Jimmy87's latest activity

Could someone kindly provide an estimate of the level of this question? I am interested to know.

Here is another one for comparison between free Claude.ai and the paid version. The free version analyzes the following incorrectly...

“They don’t miss. Gravity alone turns this into a collision, and the product is a black hole. First, the scale: a 145 g baseball at γ =...

On the other hand, here is a financial example free Claude gets wrong, and the prompt needed to correct it: “I want to use an SBLOC to...

This is the response from Fable 5: "Good news: for a conventional (Fannie Mae/Freddie Mac) loan, this is one of the acceptable ways to...

Here is one. Note, I get varying answers at different times, but all neglect to correctly describe the extreme anisotropy of what...

Earlier in this thread, I posted about AI Futures Project: AI 2027, where a group of AI researchers try and develope plausable scenorios...

Note, 3 test problems I gave Claude 6 months ago that it got wrong, it now gets right. These had to do with local, smooth, isometric...

Yes, I've seen this. There's a recent interview on YouTube with their lead author Daniel Kokotajilo you may find interesting where he...

I don't think it's about being right or wrong on exact timelines. Irving (along with all other alignment scientists) always stress...

I have Fable 5 but they are removing this tomorrow. Can you post several inputs all the free versions struggled with so I can run it...

Out of interest, how would people rank the difficulty of this physics exemplar from Humanities Last Exam:

Would you not say more like they considerably outperform humans in terms of the latest models? AISI published a report showing they are...

Those who dismiss AI as just a stochastic parrot fail to see that LLMs behave very much as we do, or won't admit it. Do they...

Most of the world's top AI alignment scientists. Most of them are serious and devoid of hype but I would pick Geoffrey Irving as the...