Agents seem to be useful for quickly mapping a problem space through trial&error + throwing stuff at the wall and seeing what sticks.
Anything grindy. Reverse engineering. Performance optimizations.
That's where swarms shine I think. But that's a much much much smaller problem space than what these agents are being sold for.
Right, the key being a fast feedback loop. I have full confidence that the same LLMs that can do these crazy math proofs could also do crazy biology, even cancer research, but they simply don’t have the cycle time low enough because they require actual physical experiments, often on living things, often over long time horizons. Even if you perfectly automated a lab, made thousands of them, you’d still be unable to match the speed of iteration that one gets with pure math and computing problems.
Plus you'd kill a lot of people.
"You're absolutely right, that drug was lethal and that's on me. I'll add a note to check human toxicity for all compounds in the future. To verify the safe dosage, I'll administer a high dose and then check smaller doses until the patient survives — not guesswork, grounded, load-bearing experiments."
That's exactly what Sidney Farber did in Boston Children's Hospital btw in late 1940. One of his tests fast forwarded cancer.
I think its practical to solve cancer on a war footing where we would expect people to die.
And Farber's methods were pretty fast for his time - lol Farber would be a perfect name for this AI that wants to solve cancer knowing what's at risk.
What gives you full confidence? The human body/biology has basically nothing to do with math or writing code. This doesnt translate in any way. There isnt a single biotech expert on earth that agrees with you.
Has nothing to do with knowing the answer, and everything to do with infinite persistence. I believe any current-generation LLM can, given an environment where it can experiment rapidly, do anything.
It can literally only write words. And it cant even do that well. It only does well at coding and math because it can be brute forced against compilers/verifiers. There is no compiler for the human body, the closest thing we have too it is death. The chemistry and physics going on in the body is much more complex and mysterious than all this math and computer science LLMs are helping with.
LLMs aren't going to make you live forever. This is a marketing scam. They are stateless statistical models that spit out words. Thats it.
Current generation LLMs still can’t win single player games that most humans can win. Someday the LLM will be able to complete getting over it by Bennett Foddy, that day is not today
That’s a game that relies heavily on quick timing though, if there’s no minimum period of time I’m sure there would be less of an issue.
No, I think if you paused the game while the LLM is thinking it will still fail.
Even outside of controls based games, LLMs fail on sokoban like puzzles weirdly enough, see MazeBench, they’re also not that good at chess, probably around 1600 elo.