Unless I am repeatedly missing it, it’s not mentioned in the article how much money the researchers spent performing the tests. What was the budget for the AI execution? If the researchers only spent $10,000 to “earn” $400,000, that’s amazing, whereas if they spent $500,000 for the same result, that’s obviously less exciting.
This resonated with me based on my recent experience using Claude to help me code. I almost gave up, but re-phrased the initial request (after 7-10 failed tries) and it finally nailed it.
> 3. Performance improves with multiple attempts
Allowing the o1 model 7 attempts instead of 1 nearly tripled its success rate, going from 16.5% to 46.5%. This hints that current models may have the knowledge to solve many more problems but struggle with execution on the first try.
I haven't really messed with Claude or other programming AIs much, but when using chatgpt for random stuff, it seems like the safety rails end up blocking a lot of stuff and rephrasing to get around them is necessary. I wonder if some of these programming AIs would be more useful if it some of the context that causes them to produce invalid results was more obvious to the users.
curious if you had any examples. i'm fairly meh on llm coding myself but have a pet theory on safety rails. i've certainly hit plenty myself but not with coding with llm's.
Wait a bit. The work for IT cleanup crews that will be needed to mop up all the vibe-damage from the locust swarm of greedy binheads that are currently puking imitation code with bugs and issues no man has seen before will eventually be plentiful. (if there will be server on server left standing after all this)
Readit News
> 3. Performance improves with multiple attempts Allowing the o1 model 7 attempts instead of 1 nearly tripled its success rate, going from 16.5% to 46.5%. This hints that current models may have the knowledge to solve many more problems but struggle with execution on the first try.
https://newsletter.getdx.com/i/160797867/performance-improve...
curious if you had any examples. i'm fairly meh on llm coding myself but have a pet theory on safety rails. i've certainly hit plenty myself but not with coding with llm's.
Discussion on original paper: https://news.ycombinator.com/item?id=43086347
Is that the one that says if an article title ends in a question that means the answer is no?