Thread

The Download: why AI's latest breakthroughs and fears may be more hype than rea

49 points · 128 comments · joozio

bananaflag · 1790163465 · focus · HN ↗
> Describing them as “superintelligence” or “rogue models” ascribes agency to products rather than to the companies building them. This framing markets these companies’ products as “superhuman” and, at the same time, helps the companies evade accountability for their actions.
If someone discovered how to summon demons to aid them in robbing banks the main issue wouldn't be "but who has the responsibility for the crime, the human or the demon", it would be "OMG DEMONS".
Seriously, I don't get what sort of world these people are living in.
1. rubendev · 1790164184 · focus · HN ↗
  That's not what the LLM hacking accidents have been like at all though. To improve the analogy, it would be like summoning a totally passive demon, giving it weapons and placing it next to a bank, place a small fence around it, and then command it to perform a totally safe "exercise" that is exactly like robbing a real bank.
  LLMs do not have agency, they are just producing tokens based on a prompt that a person entered, and some of these tokens can trigger the tools that a person gave them access to.
  1. 0xDEAFBEAD · 1790165467 · focus · HN ↗
    Dwarkesh, for one, defended his use of "anthropomorphic" language.
    >Sacrificing now yields Oracle for team, but forfeits our chance, question mark. But other agents were pushing it, sending a message saying, go, sacrifice final now. And then EarlyBig eventually agreed, thinking to itself, our own utility may be already near zero. Sacrifice rational.
    <a href="https://www.youtube.com/watch?v=X50zezLFWWI#t=2m" rel="nofollow">https://www.youtube.com/watch?v=X50zezLFWWI#t=2m
    My suspicion is that many of the "LLMs do not have agency" folks just haven't learned much about the details of the incident. It was specifically with LLM agents that were trained to be more persistent than usual.
    If you're going to say that the incident details don't matter, and LLMs lack agency because it's all based on floating-point math--why can't I say that humans lack agency, because it's all based on neurons firing?
    embedding-shape · 1790166088 · focus · HN ↗
    > If you're going to say that the incident details don't matter, and LLMs lack agency because it's all based on floating-point math--why can't I say that humans lack agency, because it's all based on neurons firing?
    They're not saying this, we're saying LLMs lack agency because if you run a LLM and don't send any prompts, literally nothing happens.
    Instruct it to "Find the right answer regardless of where", it'll do exactly this. They're passive in that they don't act by themselves, somewhere, at one point, someone "told" the LLM to "do something" and that's the cause and the reason for saying "LLMs do not have agency".
    0xDEAFBEAD · 1790166732 · focus · HN ↗
    Imagine a super-competent Navy SEAL who just sleeps in the barracks unless his commander tells him to do something. Does the Navy SEAL lack agency? As a target of this Navy SEAL, should you be reassured by the fact that they'll be sleeping in the barracks unless their commander tells them to do something?
    embedding-shape · 1790170185 · focus · HN ↗
    Imagine a car, that does nothing until a person controls it. If a person uses that car to kill, who is responsible, the person or the car?
    Is it really so unbelievable that tools, objects and inanimate things don't have agency? And that they different from a person?
    0xDEAFBEAD · 1790172393 · focus · HN ↗
    Legally speaking, we hold the person responsible in that scenario.
    From a predictive perspective, the HuggingFace incident illustrates LLM agents behaving in very human-like ways. As roon put it:
    "if you have a mental picture of guys living in computers, it’ll likely prepare you for the future better than otherwise"
    <a href="https://x.com/tszzl/status/2094136131537555891" rel="nofollow">https://x.com/tszzl/status/2094136131537555891
    embedding-shape · 1790179978 · focus · HN ↗
    > the HuggingFace incident illustrates LLM agents behaving in very human-like ways
    It does not, the only thing the HF incident illustrates is how absolutely lax security and isolation these labs do even with models without guardrails, and with "risky" prompts, and even after it happened once before (years ago) they still have the very same issue today apparently.
    What exactly is human about LLM agents breaking out of "containment" and hacking 3rd party infrastructure "by accident"?
    0xDEAFBEAD · 1790221809 · focus · HN ↗
    If someone successfully breaks out of jail, that tells you something about the jail's security. It also tells you something about their skills at breaking out of jail.
    <a href="https://www.dwarkesh.com/p/openai-huggingface" rel="nofollow">https://www.dwarkesh.com/p/openai-huggingface
    embedding-shape · 1790244972 · focus · HN ↗
    If a program breaks out of a VM, that's not "wow it looks human", how can you even argue so? I'm sorry, but if you're playing devil's advocate, make it a bit more realistic next time.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.