Overwhelming majority of customers doesn't even know they can care. And most of them wouldn't anyway. So your vote doesn't matter to anyone but you, sadly.

> This theory appealed to SpaceX founder Elon Musk, who was asleep at his home in California when the rocket exploded. Within hours of hearing about the failure, Musk gravitated toward the simple answer of a projectile being shot through the rocket.

Man, the signs were always there, right? I think I only fully realized it in 2018 during the cave "incident".

Yes, significantly, but not recently. It can't search anymore. Like literally, it can't. You cannot reach a web page you know exists, like you used to.

> It messes up sometimes (very rarely)

I don't believe this for a second. It has constantly the worst output of any serious AI I've seen, by far. It's laughably wrong sometimes, usually just wrong. It can usually cope with mundane keyword searches where it's still better to just read the wiki blurb, because even those can be mangled.

It’s particularly bad if you ask it how to do something in any given application. Most of the time it just hallucinates UI elements that aren’t there at all and confidently gives you instructions on how to do said thing in a way that is literally impossible.

I think the model must be very lightweight since they’re automatically running most search queries through it and a decently powerful model like Gemini would cost far too much in compute.

Yeah I'm guessing it's using one of the gemini-flash-lite models which are really basic. What I don't get is how they settled on this idea rather than having full Gemini generate a good answer and CACHE IT rather than having this silly lite model generate a different answer a million times a day.

So you are not actually searching for anything on web. This is more about using google as a web search engine, something it could do maybe a decade ago.

I’m not sure what do you mean. Quite often I’m trying to find an answer to something whether it’s an event, rule, informational. All of them consistently answered for me on AI overview.

That's the distinction I was trying to make - looking for an answer vs. looking for some content on a website. There's overlap in those, and we used to use the web search to find answers, but you can't use chat to search web.

> there doesn't exist any situation, in any plane in any conditions, where holding the stick back the entire time would be an appropriate input

What about the Boeing crashes?

You say "normal" and then add the other paragraphs, which are very clearly not normal. Common maybe.

Why do you think they are arguing with you instead of adding to your comment?

I cannot find an interpretation that is an addendum. They are telling me I'm wrong

Slightly related (me not understanding) is why the Copilot in VS code is essentially just CLI interface. Why can't it use the IDE tools (search, LSP, ...). All it ever does is trying to execute grep.

Someone mentioned here the other day that when you try and give Claude those tools throughan MCP or skill it tends to go a bit loopy.

At the moment it seems like the way it's been trained has been tightly coupled with grep.

It does feel bizarre though that it doesn't use the symbol servers.

Because it’s far far easier to make a text-generation machine generate text that has decades of how-to explanations on the Internet than to correctly work an internal editor API that changes often and isn’t as well-documented.

Especially if you want effective results.

I replaced common grep with a semantic search wrapper for some projects. It was amusing. It has a response header that lets Claude know it is not using standard grep. Works fine. Have to out smart them ;)

Claude Copilot does seem a bit more lost on the interface side than other models, but then again all of them are. Only the baseline tier seems to have been fine tuned to the platform.

I'm not sure how you can believe that GitHub Copilot in VS Code is just a CLI interface when the former existed long before the CLI. It's not. For a certain amount of time, the two teams weren't even working together. The CLI was adding things customers were wondering when would it reach VS Code. So, it's not just a CLI harness. They added the ability to call the CLI from VS Code but GitHub Copilot in VS Code existed before the CLI and is remains a separate thing that's just interfacing with the CLI now.

All I can say is I know because I know. There's been some "synergizing" among the corporation about the CLI team running off to do their own thing and adding features to the CLI that amount to trying to force a Terminal to act like a GUI.

Claude’s prompt heavily pushes it towards grep. We have an internal cross repo semantic search mcp and to get Claude to consistently use it a skill and prompting was not enough. A pre tool use hook is the answer. Claude will even write one for you if you describe the problem to it :)

There is an option to turn on semantic indexing and search on copilot in vscode. Although I have no perceptual differences when I turn it on. The docs mention something about it.

https://code.visualstudio.com/docs/copilot/reference/workspa...

AI benefits from tools to verify its halucinations. That's much easier in a typed and compiled language. Then have a language that can't be monkey patched at runtime and the confidence increases even more.

If you mean "easy to get something out of it" then yeah, it's great.