> What makes an out-of-control pile of matrix math any different from WannaCry? Well if it's not AGI, then probably very little. But assuming we are talking about AGI (not ASI, that'd just be silly) then the difference…
> "if it classifies successfully, it must be conditioned on latents about truth" Yes, this is a truism. Successful classification does not depend on latents being about truth. However, successfully classifying between…
> [...] but they certainly don't prove what OP claimed. OP's claim was not: "LLMs know whether text is true, false, reliable, or is epistemically calibrated". But rather: "[LLMs condition] on latents *ABOUT* truth,…
> Why do people say they don't now how it works "Curve Fitting" is the objective, the function encoded in the weights is the solution, and not actually well understood. See work from Anthropic[1] and Google[2] that…
Watch a video[1][2]/read an explainer[3] about DreamerV2 then read Appendix C - Summary of Differences (to DreamerV2). [1] https://www.youtube.com/watch?v=o75ybZ-6Uu8 (Yannic Kilcher's overview) [2]…
> So can viruses, including ones that can "intelligently" modify themselves to avoid detection, and yet this isn't a major problem. How is this any different? I now regret spending half an hour writing a response to…
> I don't understand how you can look at the current or even predicted state of the technology that we have and say "we are nowhere near the point where controlling an AGI is possible". Like....just pull the plug.…
You may be interested in the addendum: https://alexanderwales.com/addendum-to-the-ai-art-apocalypse... Which attempts to address some of the stuff wasn't addressed in the original article. (Also totally unrelated: as a…
This has the same flavor as the initial criticisms of AlphaGo. "It will never be able to play anything other than Go", cue AlphaZero. "It will never be able to do so without being told the rules", cue MuZero. "It will…
> at least understand the concept. GPT-3 is absolutely capable of understanding addition. It's handicapped by BPE's (so unless you space out adjacent digits the tokenizer collapses them into one token). But if you space…
The latter might be feasible (Though I doubt databrokers will let the current laissez-faire data-rights landscape go without a fight). The former is both wrong and infeasible. Bigger models get better at copying style…
I sympathize with not knowing about Transformers in an ML sense, but there's plenty of context in the readme. Especially considering the direct links to relevant papers. Some of lucidrains other projects include the…
> What makes an out-of-control pile of matrix math any different from WannaCry? Well if it's not AGI, then probably very little. But assuming we are talking about AGI (not ASI, that'd just be silly) then the difference…
> "if it classifies successfully, it must be conditioned on latents about truth" Yes, this is a truism. Successful classification does not depend on latents being about truth. However, successfully classifying between…
> [...] but they certainly don't prove what OP claimed. OP's claim was not: "LLMs know whether text is true, false, reliable, or is epistemically calibrated". But rather: "[LLMs condition] on latents *ABOUT* truth,…
> Why do people say they don't now how it works "Curve Fitting" is the objective, the function encoded in the weights is the solution, and not actually well understood. See work from Anthropic[1] and Google[2] that…
Watch a video[1][2]/read an explainer[3] about DreamerV2 then read Appendix C - Summary of Differences (to DreamerV2). [1] https://www.youtube.com/watch?v=o75ybZ-6Uu8 (Yannic Kilcher's overview) [2]…
> So can viruses, including ones that can "intelligently" modify themselves to avoid detection, and yet this isn't a major problem. How is this any different? I now regret spending half an hour writing a response to…
> I don't understand how you can look at the current or even predicted state of the technology that we have and say "we are nowhere near the point where controlling an AGI is possible". Like....just pull the plug.…
You may be interested in the addendum: https://alexanderwales.com/addendum-to-the-ai-art-apocalypse... Which attempts to address some of the stuff wasn't addressed in the original article. (Also totally unrelated: as a…
This has the same flavor as the initial criticisms of AlphaGo. "It will never be able to play anything other than Go", cue AlphaZero. "It will never be able to do so without being told the rules", cue MuZero. "It will…
> at least understand the concept. GPT-3 is absolutely capable of understanding addition. It's handicapped by BPE's (so unless you space out adjacent digits the tokenizer collapses them into one token). But if you space…
The latter might be feasible (Though I doubt databrokers will let the current laissez-faire data-rights landscape go without a fight). The former is both wrong and infeasible. Bigger models get better at copying style…
I sympathize with not knowing about Transformers in an ML sense, but there's plenty of context in the readme. Especially considering the direct links to relevant papers. Some of lucidrains other projects include the…