The math problems they have been solving lately suggests that they do. But then again they throw thousands of agents at the problems to get them solved so I don’t know how much if it is a number thing and how much is a model thing.

It has already been forked more than 60K times, there is no way linux can recover from this.

Except small local LLMs probably aren’t good enough to carry autonomous tasks correctly (even stuff like Haiku 4.8 from Anthropic makes mistakes quite often) and good luck getting something the size of Opus working in a soda machine. They may not even be able to lay low correctly. But then again these companies have internal models which are atleast couple generations ahead of what is publicly available so maybe they have more efficient smaller ones too? I somehow find it hard to believe but I guess we will see.

Yeah seems pretty person specific, where I looked it says soluble fibers are fine, dairy is bad if you are lactose intolerant, fatty foods are bad during flare ups.

Is this real? If so, wow not even something along the lines of “fair allocation of resources among our users” or sth like that

"Susan, who has ulcerative colitis, said: “On a morning you could have toast, a hard boiled egg, or something in sauce. There was no bacon. For breakfast there was mozzarella and sliced tomatoes. There was no hot bacon or sausage.”

Oh no Mozarella and tomatoes? Atrocious. Funny thing is fatty and processed foods like bacons and sausage are in the avoid list for people for ulcerative colitis (so is dairy for some to be fair but that is more case specific I think).

I wrote the most urgent ones but yeah, pretty much everywhere.

He is in fact the typical school bully. He tries to bully his way into everything he wants (and throws a tantrum when he can’t)

You know which three countries should definitely get a new present? Yeah, exactly.

he doesn’t just boast, he also wants eight nobel prizes

Trips? I see no such thing, he just jolted back after seeing the police that is all.

Doesn’t mean people aren’t already releasing software pipelined as such or that there aren’t software companies adopting this approach.

Also a completely irrelevant comment would be “I saw a cat today and she was very pretty”, where as you only had to take a single step from that comment to the fact that some of the problems associated to LLMs don’t apply in this context and likely applies to others. So tell me how the fuck is that completely irrelevant. You people sometimes make the most useless comments to appear edgy to a bunch of random strangers in the internet.

Not only that but if by this

mostly marketing of LLM companies

you meant to say “irrelevant to marketing of LLM” companies and not something else, it also does not look like where LLM companies are pushing things towards.

It can legitimately find some hard to find bugs but it can quite often come up with stuff for which fix would complicate the code substantially without any practical gains (bugs under very hard to encounter situations etc). So it feels like the biggest problem will arose for setups where people drive this fully autonomously where bug fixes also are implemented autonomously. What would be interesting is whether if this improves when they task a seperate agent to assess practical relevance vs increased code complexity affecting code maintainability and increased interaction between subparts. Both maintainability and practicality however are “long horizon” tasks hard to evaluate without real long term experience.

so cute

https://en.wikipedia.org/wiki/Tilcayo#/media/File:Leopardus_tilcayo_(5x3_cropped).jpg

Look at this tiny house cat in a leopard costume

I did not, I actually did not think about the scientist at all. I was distracted by the tiny cat. CAT!