SuperV1234

Where's the human baseline for the benchmarks?

Also, you said:

> The best performing model scores a 66.8. So does this prove LLMs can “understand” the code? I would argue that the answer to this is “no”.

How did you reach that conclusion?

> Are they fully “doing math” in an aligned way though?

No matter what you think "aligned" means here, publicly releasing advancements in a scientific field shouldn't be gatekept or be perceived as misaligned in any possible way.

If anything, the true misalignment comes from people trying to prevent these advancements from happening or being disclosed, or putting research behind BS paywalls.

Lmao, now solving mathematical problems and releasing the solution to the public is "misaligned". The anti-AI hysteria is getting really funny.

> how poorly math has been treated by these AI corps

Yes, what a terrible thing to advance the field significantly and release the results publicly for everyone. Truly despicable.

He decided to use LLM assistance exactly because he's an extremely competent guy.

We're getting closer and closer to the day we can have an Opus-like model running locally. The dream!

This is my experience as well. Some of my coworkers ask questions in chat that could be trivially solved by querying Claude. If I were tasked with answering that question, the responsible thing to do would be to query Claude rather than risking a manually-written incorrect answer off the top of my head. So yes, I will reply with "Claude says..."

Human slop.

If someone answers your question with "Claude says..." it's a clear indication that you should've asked the question to an LLM yourself before bothering a human.

This is just the new version of LMGTFY.

> AI is the reason our software stack is overengineered to the 10th degree

Complete BS.

Expected anti-AI psychosis propaganda but was pleasantly surprised.

> 2023 > 200 upvotes

typical hn

Completely agreed. Insane how everyone's free and open-source ideals seem to disappear when they feel personally attacked or scared by a new technology.

We have open-source models, and they're getting better and better.

That makes it even worse -- spending that much time with AI should make it glaringly obvious how valuable it is.