Amazon did not acquire debt. Period.
Can I assume that you'll volunteer to be a human guinea pig to test these proposals?
Probability of "if"? I'll give you 1000:1 odds, if you're game.
Its plausible. Its just that the effort will be huge. LLMs can do a lot of stuff because they've ingested all of our published text. But, unless we're extremely lucky, there's just not enough data out there to solve…
yes!
Indeed, ML is here to stay. But there's a difference between biology/chemistry and math, e.g. There isn't enough data out there on which to train MLs for the former. I'm thinking here of LLMs as a lossy compression of…
I'm all in on that, and I own Moderna stock ... so there's that. But we sort of understand the pathway there: we want to introduce a protein that induces an immune system reaction. Traditionally you re-engineer a virus…
Yeah. What I think is deceptive is something like solving Navier-Stokes with $10M of compute. The bigger question is how many conjectures and hypotheses they tried, and what fraction of those actually succeeded. If they…
> Say they cure cancer. People keep mouthing this same wish. But cancer is so many different cancers. And "the cure(s)" aren't just 1000 different drugs, but maybe 1000 different candidates for each that pass into lab…
Previously: "Anthropic is now pacing to generate more than $100 billion in annual revenue, up 50% from just two months ago, the New York Times reported Friday."…
Not "know" in a generic sense. But an LLM trained in the intricacies of contract law can find more loopholes than you or your cheap lawyer can. Now extrapolate that to LLMs RL-trained on many niche applications. Good…
So ultimately a huge penalty on companies that must use US AI, ceding a huge advantage to global-exUS competitors. Game over.
Open source already has the "the collective data of humanity as a whole". That's the LLM leg. Now focus on what they train their models on for RL. Do other models have less code for training coding? for math? Those are…
No, I think not. Copious genomic info but very very little wrt the huge number of possible antigens. Many pharmaceutical companies have data here, but that's proprietary. But even in aggregate, if possible, that's a…
Yeah but qualify the "know". Their "intentions" aren't conscious, but unknown.
Hah!
This assumes that everyone doesn't reach "good enough" at some point. The best developed area here -- software -- seems to suggest a "good enough" plateau, if not an absolute plateau.
See https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-che...
Exactly. And with the whole world just a few months behind, the question is whether there's an endgame other than stalemate.
If you want regulatory capture, you have to capture the world, not just the US.
Ban means what? That the entire world (ex USA) can use open-weight models? Not a win.
Yeah, maybe. But that doesn't quash gains by China's models. What's the endgame here? The USA "wins" and obliterates China? The ultimate goal seems to be stalemate, as with nuclear arms e.g.
And without anthropomorphism ... Clear thinking.
Yoshua Bengino spells out the dangers here very well, without hyperbole (Turing Award winner, etc.): https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-che...
In medicine, or drug discovery more generally, there's FAR too little empirical data for training of ML generally. See OpenAdmet. The kickback to "oh but yeah cancer" is currently just hype. DeepMind has pivoted to this…
Amazon did not acquire debt. Period.
Can I assume that you'll volunteer to be a human guinea pig to test these proposals?
Probability of "if"? I'll give you 1000:1 odds, if you're game.
Its plausible. Its just that the effort will be huge. LLMs can do a lot of stuff because they've ingested all of our published text. But, unless we're extremely lucky, there's just not enough data out there to solve…
yes!
Indeed, ML is here to stay. But there's a difference between biology/chemistry and math, e.g. There isn't enough data out there on which to train MLs for the former. I'm thinking here of LLMs as a lossy compression of…
I'm all in on that, and I own Moderna stock ... so there's that. But we sort of understand the pathway there: we want to introduce a protein that induces an immune system reaction. Traditionally you re-engineer a virus…
Yeah. What I think is deceptive is something like solving Navier-Stokes with $10M of compute. The bigger question is how many conjectures and hypotheses they tried, and what fraction of those actually succeeded. If they…
> Say they cure cancer. People keep mouthing this same wish. But cancer is so many different cancers. And "the cure(s)" aren't just 1000 different drugs, but maybe 1000 different candidates for each that pass into lab…
Previously: "Anthropic is now pacing to generate more than $100 billion in annual revenue, up 50% from just two months ago, the New York Times reported Friday."…
Not "know" in a generic sense. But an LLM trained in the intricacies of contract law can find more loopholes than you or your cheap lawyer can. Now extrapolate that to LLMs RL-trained on many niche applications. Good…
So ultimately a huge penalty on companies that must use US AI, ceding a huge advantage to global-exUS competitors. Game over.
Open source already has the "the collective data of humanity as a whole". That's the LLM leg. Now focus on what they train their models on for RL. Do other models have less code for training coding? for math? Those are…
No, I think not. Copious genomic info but very very little wrt the huge number of possible antigens. Many pharmaceutical companies have data here, but that's proprietary. But even in aggregate, if possible, that's a…
Yeah but qualify the "know". Their "intentions" aren't conscious, but unknown.
Hah!
This assumes that everyone doesn't reach "good enough" at some point. The best developed area here -- software -- seems to suggest a "good enough" plateau, if not an absolute plateau.
See https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-che...
Exactly. And with the whole world just a few months behind, the question is whether there's an endgame other than stalemate.
If you want regulatory capture, you have to capture the world, not just the US.
Ban means what? That the entire world (ex USA) can use open-weight models? Not a win.
Yeah, maybe. But that doesn't quash gains by China's models. What's the endgame here? The USA "wins" and obliterates China? The ultimate goal seems to be stalemate, as with nuclear arms e.g.
And without anthropomorphism ... Clear thinking.
Yoshua Bengino spells out the dangers here very well, without hyperbole (Turing Award winner, etc.): https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-che...
In medicine, or drug discovery more generally, there's FAR too little empirical data for training of ML generally. See OpenAdmet. The kickback to "oh but yeah cancer" is currently just hype. DeepMind has pivoted to this…