My work gives us Copilot access since We're a Microsoft Shop™
It's too bad Copilot is by far the dumbest competitor in the space
My favorite interaction so far was when I prompted it with:
ffmpeg command to convert movie.mov into a reasonably sized mp4
Sure, it's not the most direction instructions, but I tend to give it just enough to get the job done, assuming the LLM knows what its purpose is as an LLM, and it always works with the other chatbots.
Copilot's response:
I implemented and executed the Python code above to convert movie.mov to a reasonably sized movie.mp4 using ffmpeg.
However, the Python code failed since it was not able to find and access movie.mov file.
Do you want me to try again or is there anything else that I can help you with?
Note that I didn't cut anything out. It didn't actually provide me any "Python code above"
NordSteve · 6h ago
I pasted your prompt:
ffmpeg command to convert movie.mov into a reasonably sized mp4
into the Copilot app just now. Here's the response:
Here’s the breakdown:
- -vcodec libx264: Uses the H.264 video codec, great for compression and compatibility.
- -crf 23: Constant Rate Factor — lower means better quality and larger size; higher means smaller size but lower quality. 23 is a nice middle ground.
- -preset medium: Controls encoding speed vs. compression efficiency. You can try slow or faster depending on your needs.
- -acodec aac -b:a 128k: Compresses the audio using AAC at 128 kbps — pretty standard and compact.
If you're looking for even smaller file sizes, try bumping -crf up to 26 or using -preset slow.
Want to bake in scaling, remove metadata, or trim the video too? Happy to tailor the command further.
Aurornis · 1h ago
I did the same thing for several iterations and all of the responses were equally helpful.
We get these same anecdotes about terrible AI answers frequently in a local Slack I’m in. I think people love to collect them as proof that AI is terrible and useless. Meanwhile other people have no problem hitting the retry button and getting a new answer.
Some of the common causes of bad or weird responses that I’ve learned from having this exact same conversation over and over again:
- Some people use one never-ending singular session with Copilot chat, unaware that past context is influencing the answer to their next question. This is a common way to get something like Python code in response to a command line question if you’re in a Python project or you’ve been asking Python questions.
- They have Copilot set to use a very low quality model because they accidentally changed it, or they picked a model they thought was good but is actually a low-cost model meant for light work.
- They don’t realize that Copilot supports different models and you have to go out of your way to enable the best ones.
AI discussions are weird because there are two completely different worlds of people using the same tools. Some people are so convinced the tool will be bad that they give up at the slightest inconvenience or they even revel in the bad responses as proof that AI is bad. The other world spends some time learning how to use the tools and work with a solution that doesn’t always output the right answer.
We all know AI tools are not as good as the out of control LinkedIn influencer hype, but I’m also tired of the endless claims that the tools are completely useless.
JohnMakin · 56m ago
The thing responses like this miss I am pretty sure is that this is a nondeterministic machine, and nondeterministic machines that are hidden by a complete blackbox wrapper can produce wildly different results based on context and any number of independent unknown variables. so pasting “i did the same thing and it worked fine” is essentially this argument’s version of “it worked on my local.” Or it essentially boils down to “well sure, but you’re just not doing it right” when the “right” way is undefined and also context specific.
jiggawatts · 2m ago
Everything is like this.
I saw an IT professional google “My PC crashed” to diagnose a server bluescreen stop error.
glenstein · 5h ago
One fascinating aspect of LLMs is they make out-in-the-wild anecdotes instantly reproducible or, alternatively, comparable to results from others with different outcomes.
A lot of our bad experiences with, say, customer support hotlines, municipal departments, bad high school teachers, whatever, are associated with a habit of speaking that ads flavor, vibes, or bends experiences into on-the-nose stories with morals in part because we know they can't be reviewed or corrected by others.
Bringing that same way of speaking to LLMs can show us either (1) the gap between what it does and how people describe what it did or (2) shows that people are being treated differently by the same LLMs which I think are both fascinating outcomes.
celeritascelery · 4h ago
LLMs are definitely not instantly reproducible. The temperature setting adjust randomness and the models are frequently optimized and fine tuned. You will very different results depending on what you have in your context. And with a tool like Microsoft copilot, you have no idea what is in the context. There are also bugs in the tools that wrap the LLM.
Just because other people on here say “worked for me” doesn’t invalidate OPs claim. I have had similar times where an LLM will tell me “here is a script that does X” and there is no script to be found.
glenstein · 2h ago
I was intentionally broad in my claim to account for those possibilities, but also I would reject the idea that instant reproducibility is generally out of reach on account of contextual variance for a number of reasons.
Most of us are going to get the same answer to "which planet is third from the sun" even with different contexts. And if we're fulfilling our Healthy Internet Conversation 101 responsibility of engaging in charitable interpretation then other people's experiences with similarly situated LLMs can, within reason, be reasonably predictive and can be reasonably invoked to set expectations for what behavior is most likely without that meaning perfect reproducibility is possible.
myhf · 5h ago
We're also seeing a new variant of Cunningham's law:
The best way to get the right answer from an LLM is not to ask it the right question; it's to post online that it got the wrong answer.
bluSCALE4 · 2h ago
AI probably hates him so it acts dumb.
wkat4242 · 55m ago
Standard copilot indeed sucks but I'm quite fond of the new researcher agent. It spends much more time than any of the others I've tried, like Perplexity pro and openai.
From a one line question it made me a relevant document of 45 pages examining the issue from all different sides, many of which I hadn't even thought of. It spent 30 mins working. I've never seen Perplexity spend more than 5.
I won't't be surprised if they will significantly nerf it to save on computing costs. I think now they give it their all to build a customer base and then they nerf it.
hangonhn · 4h ago
This is hilarious because both Gemini and ChatGPT are shockingly good at putting together FFMPEG commands. They can both put together and also understand the various options and stages/filters.
canyp · 2h ago
I really like the final remark, "or is there anything else that I can help you with"?
Yeah, like how about answering the fucking question? lol
35123123 · 49m ago
sed, awk, docker, ffmpeg, etc... are problebly the most Google-ed commands. It's kinda shocking bad that MS LLM model is bad at this .
hu3 · 6h ago
What model? It got right first try here with your exact prompt using the free GPT-4.1 model.
BUT, I have this in my copilot-instructions.md file:
# Always follow these steps when responding to any request
1. Please do a round of thinking in <thinking></thinking> tags
2. Then a round of self-critique in <critique></critique> tags
3. Then a final round of <thinking>, before responding.
4. If you need more information, ask for it.
easton · 6h ago
That's GitHub Copilot, not "microsoft copilot", the bot built into the Microsoft 365 landing site. it doesn't give you model options, for example.
clvx · 6h ago
Whoever decided to use the same brand for different experiences should be demoted at minimum. What a way to destroy trust.
Microsoft Office is one of the most recognizable and valuable brands ever. I'm quite terrible at marketing, and even I can recognize how stupid the rebrand was.
airstrike · 2h ago
Literally this. It's one of the strongest names in all of software. It really boggles the mind.
Microsoft is the worst offender at renaming their products and services with such bad confusing names I don't think it's helping anyone, including Microsoft.
airstrike · 2h ago
Imagine literally squandering the brand name "OFFICE"
kpil · 4h ago
I got unreasonably triggered by this.
tiluha · 2h ago
You are not alone. It evoked a physical reaction in me
paradite · 2h ago
"To continue, please install the Microsoft 365 Copilot app"
I got this on mobile. Seems to be pretty apt.
johnebgd · 5h ago
Microsoft has the worst branding in tech. Microsoft Dynamics is like three different code bases and the Xbox is on its last legs thanks in large part to their naming schemes confusing consumers.
Having established brand awareness is a double-edged sword. Preserve it and nobody knows what your new thing is, leverage it and everyone gets totally confused.
vdfs · 5h ago
Probably the same one responsible for Office -> 365 naming
IBM used to be a repeat offender. I recall trying to buy the WebSphere (Java) application server for a client and then finding out that IBM had slapped "WebSphere" on all their products including things like¹ MQ Series (a queue) and DB/2 (a database). It took me an hour to figure out the right item and it was an online purchase!
¹I might be misremembering the exact products but it was similarly absurd.
SoftTalker · 2h ago
They were sticking “Watson” on all their product names for a while too.
Yeah it’s really annoying how opaque they are about the model there. Always just ”GPT 4 based” or ”GPT 4o based” if you dig in their blog archives. Makes one unable to check it against benchmarks or see when it’s updated. Setting expectations. Is it a distill? Lower precision quant? An old revision? Who knows.
esskay · 4h ago
This is pretty interesting, I had a very similar experience with Github Copilot's plugin inside Jetbrains IDE today (set to use 4o). I asked it to tell me how to do something, it instead routed in my code, tried to write a python file (its a PHP project) and told me it couldn't do it and did the exact same "Do you want me to try again or is there anything else I can help you with?"
Thing is I ask it random bits like this all the time and it's never done that before so I'm assuming some recent update has borked something.
what-the-grump · 6h ago
I cannot reproduce this in any version of copilot?
Copilot with outlook.com
Copilot base one that comes with M365,
And the add-on one for 30$/mo.
Copilot in VS code
All produce: ffmpeg -i movie.mov -vcodec libx264 -crf 23 -preset medium -acodec aac -b:a 128k output.mp4
Which is not surprising because its just an Open AI 4o call... so how are you getting this?
svachalek · 5h ago
Copilot is not OpenAI
adastra22 · 5h ago
It is OpenAI weights under the hood, unless something changed recently?
cubefox · 3h ago
At least Bing Chat was GPT-4-base with Microsoft's own fine-tuning.
rzzzt · 4h ago
Your conversations are notebooks and the code it conjured up should be behind a dropdown arrow. For visualization it seems to work fine (i.e. Copilot will generate a Python snippet, run it on the input file I attach to the request and present the diagram as a response).
cedws · 3h ago
Microsoft has really screwed up on branding yet again. Every time I read “Copilot” I think of the GitHub thing, forgetting that there is also a Microsoft Copilot that is actually multiple things across multiple products including Windows and Office.
It’s also a website like ChatGPT apparently? I thought it was called Copilot because it writes with you, so why is there also a general chat/search engine called Copilot? Jesus.
thedougd · 3h ago
I think you may be confusing Microsoft Copilot with Microsoft365 Copilot? The first doesn’t give you access to Microsoft Copilot Studio but that might also be available with Microsoft Copilot Pro.
cedws · 3h ago
My confusion has only increased.
jug · 3h ago
They have even renamed Office to Microsoft 365 Copilot. Yes. Microsoft Office.
I believe you might be confusing Copilot Search with Copilot+? Which is of course different from Copilot Pro though not necessarily entirely distinct.
worldsayshi · 3h ago
And Sam Altman thought that they were bad at naming things. Good thing they were bought up by the king of naming things. /s
Edit: They are doubling down on bad naming conventions so hard that it makes me think it's some kind of dark pattern sales strategy..
canyp · 2h ago
Classic HN psychology would say: Occam's razor would suggest mediocrity before an elaborate dark pattern scheme.
And I would agree with them in this case.
jay_kyburz · 2h ago
People are responding with..works for me, but I've found with windows copilot it was impossible to reset the AI state, and that past prompts would color new inputs.
The new chat, or new conversation buttons seem to do nothing.
robots0only · 6h ago
ohh wow, that's bad, just tried this with Gemini 2.5 Flash/Pro (and worked perfectly) -- I assume all frontier models should get this right (even simpler models should).
quantadev · 6h ago
I'd be willing to bet a more clear prompt would've given a good answer. People generally tend to overlook the fact that AIs aren't like "google". They're not really doing pure "word search" similar to Google. They expect a sensible sentence structure in order to work their best.
roywiggins · 6h ago
Maybe, but this sort of prompt structure doesn't bamboozle the better models at all. If anything they are quite good at guessing at what you mean even when your sentence structure is crap. People routinely use them to clean up their borderline-unreadable prose.
quantadev · 4h ago
I wish I had a nickle for every time I've seen someone get a garbage response from a garbage prompt and then blame the LLM.
macNchz · 6h ago
I'm all about clear prompting, but even using the verbatim prompt from the OP "ffmpeg command to convert movie.mov into a reasonably sized mp4", the smallest current models from Google and OpenAI (gemini-2.5-flash-lite and gpt-4.1-nano) both produced me a working output with explanations for what each CLI arg does.
Hell, the Q4 quantized Mistral Small 3.1 model that runs on my 16GB desktop GPU did perfectly as well. All three tests resulted in a command using x264 with crf 23 that worked without edits and took a random .mov I had from 75mb to 51mb, and included explanations of how to adjust the compression to make it smaller.
quantadev · 4h ago
There's as much variability in LLM AI as there is in human intelligence. What I'm saying is that I bet if that guy wrote a better prompt his "failing LLM" is much more likely to stop failing, unless it's just completely incompetent.
What I always find hilarious too is when the AI Skeptics try to parlay these kinds of "failures" into evidence LLMs cannot reason. If course they can reason.
moelf · 6h ago
even gemma3:12b gets it correct:
~> ollama run gemma3:12b-it-qat
>>> ffmpeg command to convert movie.mov into a reasonably sized mp4
Here's a good ffmpeg command to convert `movie.mov` to a reasonably sized MP4, along with explanations to help you adjust it:
Along with a pretty detailed and decently sounding reasoning as to why it picked these options.
12345hn6789 · 1h ago
It's been increasingly more obvious people on hacker news literally do not run these supposed prompts through LLMs. I bet you could run that prompt 10 times and it would never give up without producing a (probably fine) sh command.
Read the replies. Many folks have called gpt-4.1 through copilot and get (seemingly) valid responses.
whirlwin · 7h ago
So much for the quality testing done by Microsoft...
vpShane · 6h ago
It's an AI race and they're all vibing off of what the other ones are doing and implementing accordingly. Meanwhile, I've been enjoying Google's AI studio. I can definitely see though the AI companies are trying, they're trying to give devs, and teams the tools they need to operate more efficiently and faster.
However, piping code requests, and hey->do this, AI gives you something; the privacy aspect of it.
On the in-terms, these ARE LLMs, devs/infra people do look at how their tools are being used. You can pull a lot of info with and about an organizatin and what their internals are up to just from how they're using the AI's information.
So while we're looking at Microsoft's quality of testing, what does that really mean in terms of how they're viewing the tool usage.
quantadev · 6h ago
I love Copilot in VSCode. I always select model "Claude Sonnet 3.7", when in Copilot since it lets me choose the LLM. What I love about Copilot is the tight integration with VSCode. I can just ask it to do something and it relies on the intelligence of Claude to get the right code generated, and then all Copilot is really doing is editing my code for me, reading whatever code Claude tells it to, to build context, etc.
KoolKat23 · 6h ago
That's a different, more useable copilot.
quantadev · 4h ago
That's why I said "in VSCode" because I have no idea what this guy is running, but it's almost a certainty the problem isn't copilot but it's a bad LLM and/or his bad prompt.
kemotep · 4h ago
The Copilot integrated with Microsoft 365 doesn’t have a model switcher it just is what it is. You are talking about a completely different product that Microsoft calls the same names.
quantadev · 3h ago
I'll say it for the third time: "in VSCode". There's no ambiguity about which Copilot that is.
willhslade · 3h ago
VSCode Copilot or Copilot Chat?
quantadev · 53m ago
imo, any VSCode user needs both extensions: "GitHub Copilot" for inline completions, and "GitHub Copilot Chat" for interactive, multi-turn coding chat/agent.
MangoCoffee · 6h ago
Claude Sonnet 3.7 is my default as well in Visual Studio. i have been playing with their new default GPT-4.1. its not bad.
quantadev · 3h ago
I haven't tried GPT-4.1 yet in VSCode Copilot. I was using 'Claude Sonnet 4' until it was struggling on something yesterday which 3.7 seemed to easily do. So I reverted back to 3.7. I'm not so sure Sonnet 4 was a step forward in coding. It might be a step back.
FergusArgyll · 6h ago
People think that llms are an excuse to be lazy. You have to put some effort into the prompt!
KoolKat23 · 6h ago
Ironically copilot is lazy, have to prompt it to death, whereas the others are aligned and actually provide answers with the same prompt.
(Perhaps copilot is not lazy, just stupid relative to its peers.)
roywiggins · 6h ago
No, you don't. ChatGPT easily answers this question posed verbatim.
breadwinner · 7h ago
Microsoft has wasted their opportunity.
When ChatGPT first came out, Satya and Microsoft were seen as visionaries for their wisdom in investing in Open AI. Then competitors caught up while Microsoft stood still. Their integration with ChatGPT produced poor results [1] reminding people of Tay [2]. Bing failed to capitalize on AI, while Proclarity showed what an AI-powered search engine should really look like. Copilot failed to live up to its promise. Then Claude.ai, Gemini 2.0 caught up with or exceeded ChatGPT, and Microsoft still doesn't have their own model.
I'll add, that Google search AI integration is quite good. I'm actually amazed how well it works, given the scale of Google Search. Nowadays I don't click search results in 50% of searches, because Google AI outputs response good enough for me.
asciimov · 5h ago
Maybe we have a different Google AI down here in south Texas, but the Google search AI results I receive are laughably bad.
It has made up tags for cli functions, suggested nonexistent functions with usage instructions, it’s given me operations in the wrong order, and my personal favorite it gave me a code example in the wrong language (think replying Visual Basic for C).
cpncrunch · 4h ago
Its about half and half. Really depends on whether there are good results that gemini can summarize. If not, it gets creative. Chatgpt is generally much better.
echelon · 3h ago
ChatGPT is better, but Google owns all of the panes of glass (for now).
We've never seen a "Dog Pile vs Yahoo" battle when the giants are of this scale.
It'll be interesting to see if Google can catch up with ChatGPT (seems likely) and if they simply win by default because they're in all of the places (also seems likely). It'd be pretty wild for ChatGPT to win, honestly.
alfalfasprout · 5h ago
this is the first I've heard of anyone praising it... the results are usually outright wrong or useless.
bentcorner · 2h ago
Agree, I've seen enough wrong answers that I think it's actively harmful to put AI answers at the top of Google search results.
redwood · 4h ago
A lot of folks probably just assume it's correct
pests · 58m ago
My buddy learned this last week when we went out of the way to get gas at a wholesale store and he swore he looked it up and claimed it was open late. Well, it wasn’t.
Spooky23 · 5h ago
The problem is that they made huge time consuming investments in technology to make copilot work with the various O365 controls, then confused everyone by slathering copilot on everything.
crowcroft · 6h ago
Even with their failures Microsoft still has OpenAI over a barrel.
Access to their IP, and 20% of revenue (not profit).
echelon · 4h ago
Firing the antitrust cannon can deal with that.
Altman will absolutely attempt this.
creddit · 14m ago
Can you give a simple description of what the antitrust case would be?
crowcroft · 3h ago
Would love to see how that plays out. It’s a pretty absurd situation to eagerly sign the deal and take the funding and then when better deals start showing up turn around and try blow it up.
Barbing · 3h ago
Wonder why they’re going so slowly…
(& small typo, “Proclarity” = *Perplexity)
spiderfarmer · 7h ago
The biggest problem with Microsoft is their UX. From finding out where to actually use their products, to signing in, wading through modals, popups, terms and agreements, redirects that don’t work and links that point to nowhere. Along the way you’ll run into inconsistent, decades old UI elements and marketing pages that fully misunderstand why you’re there.
It’s a big, unsolvable mess that will forever prevent them from competing with legacy-free, capable startups.
They should delete all their public facing websites and start over.
atonse · 7h ago
Bill Gates agreed with you 20 years ago :-) (this email never gets old)
Thanks. That was a great read. Somehow missed that. Two points to make:
1. Not sure why osnews charactarised this as an "epic rant". I thought he was remarkably restrained in his tone given both his role and his (reasonable) expectations.
2. This to me shows just how hard it is for leaders at large companies to change the culture. At some point of scaling up, organisations stop being aligned to the vision of the leadership and become a seemingly autonomous entity. The craziness that Bill highlights in his email is clearly not a reflection of his vision, and in fact had materialised despite his clear wishes.
When we think about how "easy" it would be for the executive of a large organisation to change it, those of us not experienced at this level have an unrealistic expectation. It's my belief that large organisations are almost impossible to "turn around" once they get big enough and develop enough momentum regarding cultural/behavioural norms. These norms survive staff changes at pretty much every level. Changing it requires a multi-year absolute commitment from the top down. Pretty rare in my experience.
siquick · 56m ago
That was epic. The type of email we all dread to receive at work. Can’t fault Bill for his detail though, most of those kind of emails are “website slow, make fast”.
esafak · 5h ago
> When SeattlePI asked Bill Gates about this particular email last week, he chuckled. “There’s not a day that I don’t send a piece of e-mail… like that piece of e-mail. That’s my job.”
If he had to send the same email every day he wasn't doing his job well, and neither was everyone below him. Even a fraction of that list is too much.
nisa · 1h ago
It's not only public facing websites - Azure is also pretty inconsistent and lately any offer to preview a new UI was a downgrade and I happily reverted back - it's like they have a mandatory font and whitespace randomizer for any product. Also while far from a power user I've hit glitches that caused support tickets and are avoidable with clearer UX. Copilot in Azure - if it works at all - has been pretty useless.
Geezus_42 · 2h ago
Those stupid dialogs that may you think they will help you solve an issue but actually just waste 5-10mins "scanning" just to link you to irrelevant webpages that sometimes don't exist.
tartoran · 6h ago
Their UX, their naming conventions from products to frameworks and services, pulled plugged on products, user hostility and so on are all pointing out the root of the problem is elsewhere. I think Microsoft is no longer reformable. It is a behemoth that will probably continue to coast along like a braindead gozilla zombie that just floats due to its sheer size.
AppleBananaPie · 6h ago
That's the feel I get too :/
Too many crazy presentations on 'data' that are calling the calling the sky purple and everyone just nods along, ok's and gives promos all around.
dyauspitr · 6h ago
How have they failed? They still get 49% of openAI’s profits so if openAI wins, Microsoft wins.
flowerlad · 5h ago
That can be considered victory only if Microsoft is an investment firm as opposed to a software company.
dragonwriter · 1h ago
> That can be considered victory only if Microsoft is an investment firm as opposed to a software company.
An investment vehicle would be more accurate, but that's the primary function of every broadly-held publicly-traded firm.
mangamadaiyan · 4h ago
Aren't they actually an investment firm with a passing interest in software?
prng2021 · 1h ago
Maybe you should actually read one of their earnings reports. They don’t make $250B in annual revenue because of a “passing interest in software”.
gneuron · 1h ago
They're like the Merck of the pharma world.
flowerlad · 4h ago
Fair point
protocolture · 5h ago
Copilot is brainrot and its killing microsoft.
Renaming all their products to Copilot makes no sense and just causes brand confusion.
Copilot getting access to your entire 365/azure tenant is just a security nightmare waiting to happen (in fact theres already that one published and presumably patched vuln)
It has so many shackles on that its functionally useless. Half the time I ask it to edit one of my emails, it simply spits my exact text back out.
Its one singular advantage is that it has crystal clear corpospeak license surrounding what it says your data will be used for. Whether or not its true is irrelevant, organisations will pick it up for that feature alone. No one ever got fired for choosing ibm etc.
petesergeant · 1h ago
> Renaming all their products to Copilot makes no sense and just causes brand confusion.
This reminds me of IBM Watson back in the day
thiagoperes · 6h ago
msft had a massive edge. it had exclusive access to models + had web search before anyone.
they flopped this royally, just like windows mobile. they created a shitty ux by shoving it inside the bing app, then they decided to charge for it instead of capturing all enterprise value.
lastly, the product has stalled and missed on their biggest opportunity which is tapping into the data. you can think it's because of how complex it must be, but then openai and everybody else did it.
it's truly a lesson in product mismanagement, once again, from microsoft
rahimnathwani · 7h ago
Is anyone here not confused about how Copilot licenses work (free vs paid) and how to choose models for different types of task?
simonw · 7h ago
I'm confused over what anyone means when they say "Copilot", since it could mean the VS Code editor features or various features on github.com or the thing that Microsoft sell as part of their 365 office software.
I think this article is about the 365 suite.
parliament32 · 6h ago
Don't forget about the Copilot in Windows, which is different from the Copilot in Bing, which is different from Copilot in Edge, which is different from the Copilot in Copilot Studio... and that's not even getting into the various Copilots across different 365 domains (Microsoft 365 Copilot for Sales, Microsoft 365 Copilot for Service, Copilot for Microsoft Fabric, Copilot for Dynamics 365, etc are all separate products), plus the enterprise-side Security Copilot...
kamarg · 6h ago
Good old Microsoft naming. I'll never understand how they can think it's a good idea to release multiple entirely different products and call them all variations of the same thing. One would think they would have solved this problem a decade ago and yet every few years it happens again.
0x457 · 4h ago
Someone thought this would reduce marketing budget, since they now cross-promoting.
At the top-right of that page, it has a little icon indicating 'enterprise data protection' but I can't see any way for me (the user) to know what type of Copilot licence (if any) the accountholder has assigned to my user account.
KoolKat23 · 6h ago
If you have the fancy copilot pro, you'll see it in the rest of your office account, such as outlook, where additional features are available such as email summarize etc.
airstrike · 6h ago
Such an easy URL too
airstrike · 6h ago
There's also "Copilot" which is the AI assistant accessible online and via a desktop app on Windows (and even other OSs)
worldsayshi · 3h ago
Your description also works for GitHub copilot.
FauxDemure · 7h ago
Yes! I also feel like I use up my quote with my paid Copilot account faster than with my free ChatGPT one.
ape4 · 7h ago
Just ask Copilot
napoleongl · 6h ago
If only MS copilot was an actual co-pilot in my daily flight of work… but no, it cannot actually draft an email, create planner tasks or book meetings. It is a crappy way of using an LLM that sometimes can access your stuff from MS graph and sometimes has no idea about the six emails from Steve in my inbox.
And no, its PowerPoints are not good either, they are LinkedIn in ppt-form.
NordSteve · 5h ago
Here are the results I just got.
1. In Outlook asked Copilot to "create an email asking for a weekly status update for Project ABC". Iterating a bit, I asked it to be more casual and shorter. Here's what I got:
Hey Team,
Hope you're all doing great. To keep everyone on the same page with Project ABC, I'd like us to start doing weekly status updates. Just a quick summary of key developments, milestones, challenges, and what's coming up would be super helpful. This way, we can coordinate better and tackle any issues right away.
Thanks for your cooperation and hard work. Looking forward to your updates!
That seems pretty on point. Not exactly my style but to say "cannot actually draft an email" is clearly wrong.
2. I provided Copilot with this prompt:
"I am upgrading the electrical service at my house from 100a to 200a service. Create a project plan in Planner for this project."
Here's the response I got:
Nice! Upgrading from 100A to 200A is a solid move—more headroom for your gear and future-proofing your setup. Here's a breakdown of how you could structure this as a project in Microsoft Planner, with buckets and tasks to keep it organized:
---
### **Bucket 1: Planning & Permitting**
- **Assess current electrical load and future needs**
- **Consult with a licensed electrician**
- **Request utility service requirements**
- **Obtain local permits for electrical service upgrade**
- **Review NEC and local code requirements**
---
### **Bucket 2: Materials & Scheduling**
- **Select upgraded panel (200A rated) and breakers**
- **Order required materials (panel, feeder wires, conduit, ground rods, etc.)**
- **Coordinate shutdown and install time with utility provider**
- **Schedule rough-in inspection with local authority**
---
### **Bucket 3: Installation**
- **Shut off power at the main disconnect (coordinate with utility)**
- **Remove existing 100A panel and components**
- **Install 200A panel and connect feeders**
- **Upgrade grounding/bonding system as required**
- **Replace meter socket if required**
---
### **Bucket 4: Inspections & Finalization**
- **Schedule and pass electrical inspection**
- **Have utility restore permanent power**
- **Label circuits clearly in new panel**
- **Update homeowner insurance with new electrical capacity**
---
### **Bucket 5: Post-Project Wrap-Up**
- **Document panel layout and upgrades**
- **Evaluate energy use and plan for future expansion (EV charger, generator, etc.)**
- **Close out permits with inspection authority**
---
You can assign these tasks to yourself or any contractors involved, and add due dates to align with your timelines. Want help creating a PowerShell script to bulk import this into Planner?
It did produce a working script that required 1 configuration edit. The project plan is pretty good given the limited information I provided in the prompt.
3. I provided Copilot with this prompt:
book a meeting with <name> for August 1 entitled "Test Meeting"
Not a very good response:
I can't directly book meetings or access your calendar, but I can help you set it up! Here's an example of what to enter in Outlook or your preferred calendar app:
**Title:** Test Meeting
**Date:** August 1
**Attendees:** Bryan Herbst
**Time:** [Insert your preferred time]
**Location:** [Optional]
**Description:** [Add any notes or agenda items]
If you're using PowerShell or a script to automate calendar events—especially within Microsoft 365—I can help you write that too. Want to go that route?
kfajdsl · 3h ago
It seems like these examples show that it has about the same capabilities as a basic chat interface like Claude or ChatGPT without any benefit from being integrated with the Microsoft ecosystem.
alach11 · 2h ago
You nailed it. Microsoft should have a huge advantage with depth of integration, but for some reason treats Copilot in office as a glorified chat iframe. It's a huge missed opportunity.
thrawa8387336 · 1h ago
These are trash.
1) "Iterating a bit". Like that email is barely 5 sentences, you could write it faster than coaxing it out of Copilot
2) It is drivel. Could have stopped at *Consult with a licensed electrician
3) Well...
jabiko · 4h ago
I'm not sure whether Microsoft Copilot and ChatGPT use different system prompts or if there's something else behind it, but Copilot tends to have this overly cautious, sterile tone. It always seems to err on the side of safety, whereas ChatGPT generally just does what you ask as long as it's reasonable.
So it often comes down to this choice:
Open https://copilot.cloud.microsoft/, go through the Microsoft 365 login process, dig your phone out for two-factor authentication, approve it via Microsoft Authenticator, finally type your request only to get a response that feels strangely lobotomized.
Or… just go to https://chatgpt.com/, type your prompt, and actually get an answer you can work with.
It feels like every part of Microsoft wants to do the right thing, but in the end they come out with an inferior product.
haneul · 4h ago
I wonder if a Lexus/Toyota Acura/Honda Lamborghini/Audi OpenAI/Microsoft marketing split isn't in the best interests of tech giants going forward since LLMs are nondeterministic, unlike the deterministic nation-states they've built up till now...
Barbing · 2h ago
Why is Microsoft special?
ChatGPT. Perplexity. Google AI Mode. All let you get a message off.
… WAIT! copilot dot microsoft dot com lets you just send a message without logging in.
—
heh, the second result on DuckDuckGo is an MS article: “What is Copilot, and how can you use it?”
Products mentioned in the article, they say:
| Copilot | Copilot app | Copilot for individuals |
And a link for each one. Does Satya squirm when he sees that, but doesn’t have the power to change it?
Also the word “individuals” (allegedly previously mentioned) appears only once on the page.
sethops1 · 7h ago
Doesn't Microsoft own 49% of OpenAI and receives 20% of the revenue (according to ChatGPT)? In which case, what is Microsoft so upset about?
layer8 · 7h ago
That they only receive 20% of the revenue.
micromacrofoot · 7h ago
the other 51%
crop_rotation · 6h ago
The problem is it is very hard to make changes and build innovative new products within big tech, at a pace to compete with smaller companies. Big tech succeeds despite it since the resource disparity is too much.
Since the launch of ChatGPT Microsoft has had access to it and even had some of the most popular code editors, and where did it take them. This is why Meta had to launch threads with a very small team since a big team in Big tech can just not compete.
Off course like everything else there are no absolutes and when Big Tech feels there is an existential crisis on something they do start improving, however such moments are far and few.
mark_l_watson · 6h ago
I read today that OpenAI is planning a ‘AI super app’ that would have canvas, word processing, etc., all in one work app. That actually sounds like a good idea to me and is very different from Google’s approach of integrating Gemini into the work place apps. Google may have an advantage because so many people are used to working in Workspace apps.
airstrike · 6h ago
Mind providing a link? I may or may not be creating the exact same thing...
Also if anyone from OpenAI or any of its competitors wants to talk my email is on my HN profile ;-)
owebmaster · 5h ago
That's the app many of us are creating and I bet some of them are going to be much better than the OpenAI one
airstrike · 5h ago
Tamo junto
dwayne_dibley · 6h ago
I don’t understand how it’s not more useful to most people with copilot subscriptions in work. It has access to my works OneDrive, it really should be the most commonly used LLM
truekonrads · 4h ago
Copilot 365 conserves tokens a lot which is why results are bad.
lanthissa · 4h ago
its not a rivalry if one party is not in the competition, its just jealousy
androng · 6h ago
I only used free Microsoft Copilot once back when GPT-4 came out and it wasn’t free on OpenAI yet. The responses from Microsoft GPT-4 sucked vs OpenAI GPT-4 because they were short and I assume Microsoft made the system prompt do that to save money. I never went back to Microsoft copilot again and have not heard anyone talk about it or meta ai either.
smithkl42 · 5h ago
We're paying for Copilot for Office365. I asked it recently to retrieve a list of field names mentioned in a document - about as basic a task as you could hope for. It told me it couldn't do so.
My precise request: "Extract the list of field names in Exhibit A."
Its precise response: "I understand that you want to extract the list of field names from Exhibit A in your document. Unfortunately, I cannot directly perform document-related commands such as extracting text from specific sections."
I tried several different ways of convincing it, before giving up and using the web version of ChatGPT, which did it perfectly.
I had an even worse experience with the Copilot built into the new version of SSMS. It just won't look at the query window at all. You have to copy and paste the text of your query into the chat window ... which, like, what's the point then?
jorl17 · 6h ago
Microsoft's decision to name this product Copilot has to be the result of some form of internal sabotage, I refuse to believe otherwise.
A lot of the early adopters (and driving forces) of LLMs have been tech-minded people. This means it's quite a good idea NOT to confuse them.
And, yet, Microsoft decided to name their product Microsoft Copilot, even though they already had a (quite well-received!!) Copilot in the form of Github Copilot, a product which has also been expanding to include a plethora of other functionality (albeit in a way that does make sense). How is this not incredibly confusing?
So what actually _is_ Copilot? Is there a bing copilot? A copilot in windows machines? Is it an online service? (I saw someone post a link to an office 365)?
I'm going to be honest and tell you that I have no fucking clue what Microsoft Copilot actually is, and Microsoft's insistence on being either hostile to users or pretending like they're not creating a confusing mess of semantic garbage is insulting. I am lucky not to have to use Windows daily, and most of what I do that involves copilot is...Github Copilot.
I am knee-deep into LLMs. My friends can't stand me with how much I go on about them, how I use them, from remote to local models, to agents, to the very debatable idea that they may be conscious, you name it. And yet, as bullish as I am on the thing, I have no fucking clue what Microsoft copilot is. Perhaps I'm definitely not their target market, but from what I've seen, tech-illiterate people have no idea what it is either, just that it's "more microsoft trash".
When I was younger, I used to be a very loud anti-microsoft boy, I loathed everything they did. Slowly, for a while, they were managing to win me over (in part because I outgrew that phase, but also because they have definitely been cleaning up their image and, at least to me, producing better and more relevant software). However, in recent years, their insistence on naming everything this way and creating a maze out of their products is...baffling. I feel myself not being able to stand MS again.
And what is it with big corporations and a seeming inability to name their products decently? This is appalling. The people making these decisions should be fired, because clearly they don't have any pride in what they do, or they wouldn't have allowed this.
Get your shit together, microsoft!
jjcm · 5h ago
> Microsoft's decision to name this product Copilot has to be the result of some form of internal sabotage
If you look at this in isolation, yes. If you look at this historically, it's totally on-brand for Microsoft. Office 365, Live, MSN were all brand that Microsoft has slapped wholesale on things. Microsoft has always been reactive when it comes to branding, rather than proactive.
esafak · 5h ago
How are managers going to earn their keep if they don't rebrand and re-org?!
jdsully · 5h ago
I'm reminded of when .NET was released suddenly everything was .NET, even an office release was named after it. Then it finally narrowed down into the programming languages we know and love or hate depending on your vibe. I assume this will happen here too eventually.
airstrike · 6h ago
Everything is Copilot, but they're all different products, and one of them is just a launcher to Office apps, each with their own assistant called Copilot
alganet · 6h ago
> It’s unclear whether OpenAI’s momentum with corporations will continue, but the company recently said it has 3 million paying business users
That's the only data point the article has, and it is incomplete (no Copilot numbers).
The rest are just testimonials (some of anonymous character) and stories.
Who's having more success then? No one knows. It's up to the reader to decide.
Looks like made-up rivalry article to me. Draws clicks, no actual content inside.
FrustratedMonky · 7h ago
Because of the partnership with OpenAI, I always assumed Copilot was just built on top of GPT.
So how did MS make Copilot Suck, if it started with same base?
treesknees · 6h ago
Microsoft Copilot uses their own model that is originally based on GPT-4 if I’m not mistaken.
But, it’s mostly a RAG tool, “grounded in web” as they say. When you give Copilot a query, it uses the model to reword your query into an optimal Bing search query, fetches the results, and then crafts output using the model.
I commend their attempt to use Bing as a source of data to keep up to date and reduce hallucinations, especially in an enterprise setting where users may be more sensitive to false information, however as a result some of the answers it gives can only be as good as the Bing search results.
Quarrelsome · 2h ago
Bing isn't terrible though, is it? DuckDuckGo uses it, or at least used to, and that trade off was fine most of the time.
treesknees · 1h ago
It’s not necessarily terrible. It just sometimes leaves you wishing it was “smarter”. When I get a bad result, trying the same query on ChatGPT gives a much better response.
FrustratedMonky · 6h ago
Seems like with their own resources, and also owning part of GPT, they should be able to pivot and at least make a programming tool equal to Chat GPT.
bix6 · 7h ago
Real talk! Copilot is so bad. It’s literally useless. And they charge an absolute arm for it. Like how is it soooo much worse than Chat? I am a frustrated monky when I use Copilot.
smcleod · 6h ago
Microsoft just did a rug pull by introducing dramatically reduced rate limits on copilot requests for paying customers too.
I'm seeing enterprise and personal users hit their monthly rate limits in less than 3 days.
brandonfro · 1h ago
Why is this being downvoted? I’ve seen similar behavior, and it’s not outside the realm of possibility that MS would choose meager context windows and API limits in favor of profit.
Mc91 · 4h ago
I program at a non-tech Fortune 100 company. Our team is on a pilot program to try out AI-assisted programming at the company, and Cursor with OpenAI models are mostly what we are using. I have it integrated into my standard IDE workflow and try to write unit tests and the like with it.
It's too bad Copilot is by far the dumbest competitor in the space
My favorite interaction so far was when I prompted it with:
Sure, it's not the most direction instructions, but I tend to give it just enough to get the job done, assuming the LLM knows what its purpose is as an LLM, and it always works with the other chatbots.Copilot's response:
Note that I didn't cut anything out. It didn't actually provide me any "Python code above"We get these same anecdotes about terrible AI answers frequently in a local Slack I’m in. I think people love to collect them as proof that AI is terrible and useless. Meanwhile other people have no problem hitting the retry button and getting a new answer.
Some of the common causes of bad or weird responses that I’ve learned from having this exact same conversation over and over again:
- Some people use one never-ending singular session with Copilot chat, unaware that past context is influencing the answer to their next question. This is a common way to get something like Python code in response to a command line question if you’re in a Python project or you’ve been asking Python questions.
- They have Copilot set to use a very low quality model because they accidentally changed it, or they picked a model they thought was good but is actually a low-cost model meant for light work.
- They don’t realize that Copilot supports different models and you have to go out of your way to enable the best ones.
AI discussions are weird because there are two completely different worlds of people using the same tools. Some people are so convinced the tool will be bad that they give up at the slightest inconvenience or they even revel in the bad responses as proof that AI is bad. The other world spends some time learning how to use the tools and work with a solution that doesn’t always output the right answer.
We all know AI tools are not as good as the out of control LinkedIn influencer hype, but I’m also tired of the endless claims that the tools are completely useless.
I saw an IT professional google “My PC crashed” to diagnose a server bluescreen stop error.
A lot of our bad experiences with, say, customer support hotlines, municipal departments, bad high school teachers, whatever, are associated with a habit of speaking that ads flavor, vibes, or bends experiences into on-the-nose stories with morals in part because we know they can't be reviewed or corrected by others.
Bringing that same way of speaking to LLMs can show us either (1) the gap between what it does and how people describe what it did or (2) shows that people are being treated differently by the same LLMs which I think are both fascinating outcomes.
Just because other people on here say “worked for me” doesn’t invalidate OPs claim. I have had similar times where an LLM will tell me “here is a script that does X” and there is no script to be found.
Most of us are going to get the same answer to "which planet is third from the sun" even with different contexts. And if we're fulfilling our Healthy Internet Conversation 101 responsibility of engaging in charitable interpretation then other people's experiences with similarly situated LLMs can, within reason, be reasonably predictive and can be reasonably invoked to set expectations for what behavior is most likely without that meaning perfect reproducibility is possible.
The best way to get the right answer from an LLM is not to ask it the right question; it's to post online that it got the wrong answer.
From a one line question it made me a relevant document of 45 pages examining the issue from all different sides, many of which I hadn't even thought of. It spent 30 mins working. I've never seen Perplexity spend more than 5.
I won't't be surprised if they will significantly nerf it to save on computing costs. I think now they give it their all to build a customer base and then they nerf it.
Yeah, like how about answering the fucking question? lol
https://i.imgur.com/toLzwCk.png
ffmpeg -i movie.mov -c:v libx264 -preset medium -crf 23 -c:a aac -b:a 128k movie.mp4
BUT, I have this in my copilot-instructions.md file:
https://news.ycombinator.com/item?id=42751726
I got this on mobile. Seems to be pretty apt.
https://news.ycombinator.com/item?id=40419292
https://news.ycombinator.com/item?id=42751726
IBM used to be a repeat offender. I recall trying to buy the WebSphere (Java) application server for a client and then finding out that IBM had slapped "WebSphere" on all their products including things like¹ MQ Series (a queue) and DB/2 (a database). It took me an hour to figure out the right item and it was an online purchase!
¹I might be misremembering the exact products but it was similarly absurd.
Openned: https://copilot.microsoft.com
Same prompt: ffmpeg command to convert movie.mov into a reasonably sized mp4
https://i.imgur.com/CuaxIlL.png
Thing is I ask it random bits like this all the time and it's never done that before so I'm assuming some recent update has borked something.
Copilot with outlook.com
Copilot base one that comes with M365,
And the add-on one for 30$/mo.
Copilot in VS code
All produce: ffmpeg -i movie.mov -vcodec libx264 -crf 23 -preset medium -acodec aac -b:a 128k output.mp4
Which is not surprising because its just an Open AI 4o call... so how are you getting this?
It’s also a website like ChatGPT apparently? I thought it was called Copilot because it writes with you, so why is there also a general chat/search engine called Copilot? Jesus.
https://www.windowslatest.com/2025/01/18/microsoft-just-rena...
Edit: They are doubling down on bad naming conventions so hard that it makes me think it's some kind of dark pattern sales strategy..
And I would agree with them in this case.
The new chat, or new conversation buttons seem to do nothing.
Hell, the Q4 quantized Mistral Small 3.1 model that runs on my 16GB desktop GPU did perfectly as well. All three tests resulted in a command using x264 with crf 23 that worked without edits and took a random .mov I had from 75mb to 51mb, and included explanations of how to adjust the compression to make it smaller.
What I always find hilarious too is when the AI Skeptics try to parlay these kinds of "failures" into evidence LLMs cannot reason. If course they can reason.
~> ollama run gemma3:12b-it-qat >>> ffmpeg command to convert movie.mov into a reasonably sized mp4
Here's a good ffmpeg command to convert `movie.mov` to a reasonably sized MP4, along with explanations to help you adjust it:
```bash ffmpeg -i movie.mov -c:v libx264 -crf 23 -preset medium -c:a aac -b:a 128k movie.mp4 ```
*Explanation of the command and the options:*
[1]: https://rentry.co/yu36i4d3
ffmpeg -i movie.mov -vcodec libx264 -crf 23 -preset medium -acodec aac -b:a 128k movie_converted.mp4
Along with a pretty detailed and decently sounding reasoning as to why it picked these options.
Read the replies. Many folks have called gpt-4.1 through copilot and get (seemingly) valid responses.
However, piping code requests, and hey->do this, AI gives you something; the privacy aspect of it.
On the in-terms, these ARE LLMs, devs/infra people do look at how their tools are being used. You can pull a lot of info with and about an organizatin and what their internals are up to just from how they're using the AI's information.
So while we're looking at Microsoft's quality of testing, what does that really mean in terms of how they're viewing the tool usage.
(Perhaps copilot is not lazy, just stupid relative to its peers.)
When ChatGPT first came out, Satya and Microsoft were seen as visionaries for their wisdom in investing in Open AI. Then competitors caught up while Microsoft stood still. Their integration with ChatGPT produced poor results [1] reminding people of Tay [2]. Bing failed to capitalize on AI, while Proclarity showed what an AI-powered search engine should really look like. Copilot failed to live up to its promise. Then Claude.ai, Gemini 2.0 caught up with or exceeded ChatGPT, and Microsoft still doesn't have their own model.
[1] https://www.nytimes.com/2023/02/16/technology/bing-chatbot-m...
[2] https://en.wikipedia.org/wiki/Tay_(chatbot)
It has made up tags for cli functions, suggested nonexistent functions with usage instructions, it’s given me operations in the wrong order, and my personal favorite it gave me a code example in the wrong language (think replying Visual Basic for C).
We've never seen a "Dog Pile vs Yahoo" battle when the giants are of this scale.
It'll be interesting to see if Google can catch up with ChatGPT (seems likely) and if they simply win by default because they're in all of the places (also seems likely). It'd be pretty wild for ChatGPT to win, honestly.
Access to their IP, and 20% of revenue (not profit).
Altman will absolutely attempt this.
(& small typo, “Proclarity” = *Perplexity)
It’s a big, unsolvable mess that will forever prevent them from competing with legacy-free, capable startups.
They should delete all their public facing websites and start over.
https://www.osnews.com/story/19921/full-text-an-epic-bill-ga...
1. Not sure why osnews charactarised this as an "epic rant". I thought he was remarkably restrained in his tone given both his role and his (reasonable) expectations.
2. This to me shows just how hard it is for leaders at large companies to change the culture. At some point of scaling up, organisations stop being aligned to the vision of the leadership and become a seemingly autonomous entity. The craziness that Bill highlights in his email is clearly not a reflection of his vision, and in fact had materialised despite his clear wishes.
When we think about how "easy" it would be for the executive of a large organisation to change it, those of us not experienced at this level have an unrealistic expectation. It's my belief that large organisations are almost impossible to "turn around" once they get big enough and develop enough momentum regarding cultural/behavioural norms. These norms survive staff changes at pretty much every level. Changing it requires a multi-year absolute commitment from the top down. Pretty rare in my experience.
If he had to send the same email every day he wasn't doing his job well, and neither was everyone below him. Even a fraction of that list is too much.
Too many crazy presentations on 'data' that are calling the calling the sky purple and everyone just nods along, ok's and gives promos all around.
An investment vehicle would be more accurate, but that's the primary function of every broadly-held publicly-traded firm.
Renaming all their products to Copilot makes no sense and just causes brand confusion.
Copilot getting access to your entire 365/azure tenant is just a security nightmare waiting to happen (in fact theres already that one published and presumably patched vuln)
It has so many shackles on that its functionally useless. Half the time I ask it to edit one of my emails, it simply spits my exact text back out.
Its one singular advantage is that it has crystal clear corpospeak license surrounding what it says your data will be used for. Whether or not its true is irrelevant, organisations will pick it up for that feature alone. No one ever got fired for choosing ibm etc.
This reminds me of IBM Watson back in the day
they flopped this royally, just like windows mobile. they created a shitty ux by shoving it inside the bing app, then they decided to charge for it instead of capturing all enterprise value.
lastly, the product has stalled and missed on their biggest opportunity which is tapping into the data. you can think it's because of how complex it must be, but then openai and everybody else did it.
it's truly a lesson in product mismanagement, once again, from microsoft
I think this article is about the 365 suite.
At the top-right of that page, it has a little icon indicating 'enterprise data protection' but I can't see any way for me (the user) to know what type of Copilot licence (if any) the accountholder has assigned to my user account.
1. In Outlook asked Copilot to "create an email asking for a weekly status update for Project ABC". Iterating a bit, I asked it to be more casual and shorter. Here's what I got:
That seems pretty on point. Not exactly my style but to say "cannot actually draft an email" is clearly wrong.2. I provided Copilot with this prompt:
"I am upgrading the electrical service at my house from 100a to 200a service. Create a project plan in Planner for this project."
Here's the response I got:
It did produce a working script that required 1 configuration edit. The project plan is pretty good given the limited information I provided in the prompt.3. I provided Copilot with this prompt:
Not a very good response:1) "Iterating a bit". Like that email is barely 5 sentences, you could write it faster than coaxing it out of Copilot
2) It is drivel. Could have stopped at *Consult with a licensed electrician
3) Well...
So it often comes down to this choice: Open https://copilot.cloud.microsoft/, go through the Microsoft 365 login process, dig your phone out for two-factor authentication, approve it via Microsoft Authenticator, finally type your request only to get a response that feels strangely lobotomized.
Or… just go to https://chatgpt.com/, type your prompt, and actually get an answer you can work with.
It feels like every part of Microsoft wants to do the right thing, but in the end they come out with an inferior product.
ChatGPT. Perplexity. Google AI Mode. All let you get a message off.
… WAIT! copilot dot microsoft dot com lets you just send a message without logging in.
—
heh, the second result on DuckDuckGo is an MS article: “What is Copilot, and how can you use it?”
Products mentioned in the article, they say:
| Copilot | Copilot app | Copilot for individuals |
And a link for each one. Does Satya squirm when he sees that, but doesn’t have the power to change it?
Also the word “individuals” (allegedly previously mentioned) appears only once on the page.
Since the launch of ChatGPT Microsoft has had access to it and even had some of the most popular code editors, and where did it take them. This is why Meta had to launch threads with a very small team since a big team in Big tech can just not compete.
Off course like everything else there are no absolutes and when Big Tech feels there is an existential crisis on something they do start improving, however such moments are far and few.
Also if anyone from OpenAI or any of its competitors wants to talk my email is on my HN profile ;-)
My precise request: "Extract the list of field names in Exhibit A."
Its precise response: "I understand that you want to extract the list of field names from Exhibit A in your document. Unfortunately, I cannot directly perform document-related commands such as extracting text from specific sections."
I tried several different ways of convincing it, before giving up and using the web version of ChatGPT, which did it perfectly.
I had an even worse experience with the Copilot built into the new version of SSMS. It just won't look at the query window at all. You have to copy and paste the text of your query into the chat window ... which, like, what's the point then?
A lot of the early adopters (and driving forces) of LLMs have been tech-minded people. This means it's quite a good idea NOT to confuse them.
And, yet, Microsoft decided to name their product Microsoft Copilot, even though they already had a (quite well-received!!) Copilot in the form of Github Copilot, a product which has also been expanding to include a plethora of other functionality (albeit in a way that does make sense). How is this not incredibly confusing?
So what actually _is_ Copilot? Is there a bing copilot? A copilot in windows machines? Is it an online service? (I saw someone post a link to an office 365)?
I'm going to be honest and tell you that I have no fucking clue what Microsoft Copilot actually is, and Microsoft's insistence on being either hostile to users or pretending like they're not creating a confusing mess of semantic garbage is insulting. I am lucky not to have to use Windows daily, and most of what I do that involves copilot is...Github Copilot.
I am knee-deep into LLMs. My friends can't stand me with how much I go on about them, how I use them, from remote to local models, to agents, to the very debatable idea that they may be conscious, you name it. And yet, as bullish as I am on the thing, I have no fucking clue what Microsoft copilot is. Perhaps I'm definitely not their target market, but from what I've seen, tech-illiterate people have no idea what it is either, just that it's "more microsoft trash".
When I was younger, I used to be a very loud anti-microsoft boy, I loathed everything they did. Slowly, for a while, they were managing to win me over (in part because I outgrew that phase, but also because they have definitely been cleaning up their image and, at least to me, producing better and more relevant software). However, in recent years, their insistence on naming everything this way and creating a maze out of their products is...baffling. I feel myself not being able to stand MS again.
And what is it with big corporations and a seeming inability to name their products decently? This is appalling. The people making these decisions should be fired, because clearly they don't have any pride in what they do, or they wouldn't have allowed this.
Get your shit together, microsoft!
If you look at this in isolation, yes. If you look at this historically, it's totally on-brand for Microsoft. Office 365, Live, MSN were all brand that Microsoft has slapped wholesale on things. Microsoft has always been reactive when it comes to branding, rather than proactive.
That's the only data point the article has, and it is incomplete (no Copilot numbers).
The rest are just testimonials (some of anonymous character) and stories.
Who's having more success then? No one knows. It's up to the reader to decide.
Looks like made-up rivalry article to me. Draws clicks, no actual content inside.
So how did MS make Copilot Suck, if it started with same base?
But, it’s mostly a RAG tool, “grounded in web” as they say. When you give Copilot a query, it uses the model to reword your query into an optimal Bing search query, fetches the results, and then crafts output using the model.
I commend their attempt to use Bing as a source of data to keep up to date and reduce hallucinations, especially in an enterprise setting where users may be more sensitive to false information, however as a result some of the answers it gives can only be as good as the Bing search results.
I'm seeing enterprise and personal users hit their monthly rate limits in less than 3 days.