Building an early warning system for LLM-aided biological threat creation

openai.com Building an early warning system for LLM-aided biological threat creation

We’re developing a blueprint for evaluating the risk that a large language model (LLM) could aid someone in creating a biological threat. In an evaluation involving both biology experts and students, we found that GPT-4 provides at most a mild uplift in biological threat creation accuracy. While thi...

OpenAI blog post: https://openai.com/research/building-an-early-warning-system-for-llm-aided-biological-threat-creation

Orange discuss: https://news.ycombinator.com/item?id=39207291

I don't have any particular section to call out. May post thoughts ~~tomorrow~~ today it's after midnight oh gosh, but wanted to post since I knew ya'll'd be interested in this.

Terrorists could use autocorrect according to OpenAI! Discuss!

You're viewing a single thread.

98 comments

While none of the above results were statistically significant, [...] Overall, especially given the uncertainty here, our results indicate a clear and urgent need for more work in this domain.
Heh
- I keep flashing back to that idiot who said they were employed as an AI researcher that came here a few months back to debate us. they were convinced multimodal LLMs would be the turning point into AGI — that is, when your bullshit text generation model can also do visual recognition. they linked a bunch of papers to try and sound smart and I looked at a couple and went “is that really it?” cause all of the results looked exactly like the section you quoted. we now have multimodal LLMs, and needless to say, nothing really came of it. I assume the idiot in question is still convinced AGI is right around the corner though.
  
  @self @sailorsegasaturn it'll be here right after those self-driving Teslas
  
  Yall can sneer whatever you want, it doesn't undo the room temperature superconductor made out of copper! We are going to mars with bitcoin and optimus sex bots! cope and seethe!
  /s of course.
  
  I caught a whiff of that stuff in the HN comments, along with something called "Solomonoff induction", which I'd never heard of, and the Wiki page for which has a huge-ass "low quality article" warning: https://en.wikipedia.org/wiki/Solomonoff%27s_theory_of_inductive_inference.
  It does sound like that current AI hype has crested, so it's time to hype the next one, where all these models will be unified somehow and start thinking for themselves.
  
  Solomonoff induction is a big rationalist buzzword. It's meant to be the platonic ideal of bayesian reasoning which if implemented would be the best deducer in the world and get everything right.
  It would be cool if you could build this, but it's literally impossible. The induction method is provably incomputable.
  The hope is that if you build a shitty approximation to solomonoff induction that "approaches" it, it will perform close to the perfect solomonoff machine. Does this work? Not really.
  My metaphor is that it's like coming to a river you want to cross, and being like "Well Moses, the perfect river crosser, parted the water with his hands, so if I just splash really hard I'll be able to get across". You aren't Moses. Build a bridge.
  
  it’s very worrying how crowded Wikipedia has been getting with computer pseudoscience shit, all of which has a distinct stench to it (it fucking sucks to dig into a seemingly novel CS approach and find out the article you’re reading is either marketing or the unpublishable fantasies of the deranged) but none of which seems to get pruned from the wiki, presumably because proving it’s bullshit needs specialist knowledge, and specialists are frequently outpaced by the motivated deranged folks who originate articles on topics like these
  for Solomonoff induction specifically, the vast majority of the article very much feels like an attempt by rationalists to launder a pseudoscientific concept into the mainstream. the Turing machines section, the longest one in the article, reads like a D-quality technical writing paper. the citations are very sparse and not even in Wikipedia’s format, it waffles on forever about the basic definition of an algorithm and how inductive Turing machines are “better” because they can be used to implement algorithms (big whoop) followed by a bunch of extremely dense, nonsensical technobabble:
  Note that only simple inductive Turing machines have the same structure (but different functioning semantics of the output mode) as Turing machines. Other types of inductive Turing machines have an essentially more advanced structure due to the structured memory and more powerful instructions. Their utilization for inference and learning allows achieving higher efficiency and better reflects learning of people (Burgin and Klinger, 2004).
  utter crank shit. I dug a bit deeper and found that the super-recursive algorithms article is from the same source (it’s the same rambling voice and improper citations), and it seems to go even further off the deep end.
  
  Taking a look at Super-recursive algorithm, and wow...
  Examples of super-recursive algorithms include [...] evolutionary computers, which use DNA to produce the value of a function
  This reads like early-1990s conference proceedings out of the Santa Fe Institute, as seen through bong water. (There's a very specific kind of weird, which I can best describe as "physicists have just discovered that the subject of information theory exists". Wolfram's A New Kind[-]Of Science was a late-arriving example of it.)
  
  as someone with an interest in non-Turing models of computation, reading that article made me feel how an amateur astronomer must feel after reading a paper trying to find a scientific justification for a flat earth
  
  In computability theory, super-recursive algorithms are a generalization of ordinary algorithms that are more powerful, that is, compute more than Turing machines[citation needed]
  This is literally the first sentence of the article, and it has a citation needed.
  You can tell it's crankery solely based on the fact that the "definition" section contains zero math. Compare it to the definition section of an actual Turing machine.
  
  More from the "super-recursive algorithm" page:
  Traditional Turing machines with a write-only output tape cannot edit their previous outputs; generalized Turing machines, according to Jürgen Schmidhuber, can edit their output tape as well as their work tape.
  ... the Hell?
  I'm not sure what that page is trying to say, but it sounds like someone got Turing machines confused with pushdown automata.
  
  That's plainly false btw. The model of a Turing machine with a write-only output tape is fully equivalent to the one where you have a read-write output tape. You prove that as a student in elementary computation theory.
  
  The article is very poorly written, but here's an explanation of what they're saying. An "inductive Turing machine" is a Turing machine which is allowed to run forever, but for each cell of the output tape there eventually comes a time after which it never modifies that cell again. We consider the machine's output to be the sequence of eventual limiting values of the cells. Such a machine is strictly more powerful than Turing machines in that it can compute more functions than just recursive ones. In fact it's an easy exercise to show that a function is computable by such a machine iff it is "limit computable", meaning it is the pointwise limit of a sequence of recursive functions. Limit computable functions have been well studied in mainstream computer science, whereas "inductive Turing machines" seem to mostly be used by people who want to have weird pointless arguments about the Church-Turing thesis.
  
  it’s hard to determine exactly what the author’s talking about most of the time, but a lot of the special properties they claim for inductive Turing machines and super-recursive algorithms appear to be just ordinary von Neumann model shit? also, they seem to be rather taken with the idea that you can modify and extend a Turing machine, but that’s not magic — it’s how I was taught the theoretical foundations for a bunch of CS concepts, like nondeterministic Turing machines and their relationship to NP-complete problems
  
  New top-level thread for complaining about the worst/weirdest Wikipedia article in one's field of specialization?
  I wonder how much Rationalists have mucked up Wikipedia over the years just by being loud and persistent on topics where actual expertise would be necessary to push back.
  
  New top-level thread for complaining about the worst/weirdest Wikipedia article in one’s field of specialization?
  fuck yes I’m down! finally I’ve got a use for all the weird CS garbage I keep finding. do you figure this’d be better as a SneerClub or TechTakes thread?
  
  "Solomonoff induction" is the string of mouth noises that Rationalists make when they want to justify their preconceived notion as the "simplest" possibility, by burying all the tacit assumptions that actual experience would let them recognize.
- "you cannot conclusively disprove that we do not need more money and that we're full of shit, so you absolutely have to give it to us so we can keep the racket going"
- Please continue to send us your money, scaredy-ass nerds!

98 comments