Anthropic: Introducing The Conceptual Reasoning Index

(alignment.anthropic.com)

31 points | by optimalsolver 1 hour ago

9 comments

  • lanyard-textile 21 minutes ago
    Ah, yes -- A closed source benchmark that Anthropic paid for that Anthropic ranked highest.

    0/10

    • smallmancontrov 1 minute ago
      It's the elephant in the room, and leaving it off the bullet point list seriously calls into doubt the integrity of the enterprise:

      * The incentives of frontier AI labs are aligned with enabling AI takeover, not preventing it.

  • onomojo 2 minutes ago
    We invented a new benchmark and look we're at the top. Everyone else sucks compared to us. Especially those dirty open models.
  • andsoitis 1 hour ago
    Opening line:

    > A core hope for managing AI risks is that AIs will help us understand our situation

    Gonna stop you right there and ask that you think deeply about that premise.

    • blovescoffee 34 minutes ago
      The underlying idea is that AI capabilities will become so advanced that only AI will enable us to monitor/correct/understand behavior. Obviously this is not without issue and I don't want to try to defend their position right now. But that's what they mean
      • hn_throwaway_99 21 minutes ago
        That first sentence of yours explains exactly why it is so ridiculous. If only AI can understand it, how is there any assurance that AI will "correct" it's behavior that is aligned with what humans presumably want.
        • VeninVidiaVicii 3 minutes ago
          But also what is the evidence that something only AI can understand even “matters” or makes sense? I’m increasingly convinced commercial AI is exploiting our logical blind spot to be spoken to authoritatively.
        • skybrian 5 minutes ago
          It’s not hard to get LLM’s to inform on each other. They don’t really do loyalty.
        • esafak 10 minutes ago
          Being less smart gives no assurance that it will be aligned. At least you consider it a problem so we're on the same page!
      • kakugawa 4 minutes ago
        "Advanced" can just mean that agents perform actions at a high enough velocity that a human operator can't reasonably review it. i.e. what is already possible today.
      • MontagFTB 29 minutes ago
        I think I’ve seen that movie.
  • tolugenius 19 minutes ago
    > For example, if we ask a model for the probability P(A) and another instance of the same model for the probability P(A&B), do the reported probabilities satisfy P(A) ≥ P(A&B)?

    So that's it? Are you saying they compressed risk reduction to high school level stats calculations and a greater than or equal to? To early for this

  • behnamoh 30 minutes ago
    I don't remember any company in world's history that has both been loved and hated by the same users who purchase from it. We love Anthropic for its amazing models, and we hate them for all the shenanigans around the models, including their marketing.

    I kinda wish they had not made a comeback after Claude 2.

    • velcrovan 21 minutes ago
      I enjoy using the models. I also get that there are shenanigans and that marketing is happening, but as long as the models are this effective I can't much bring myself to care. I suspect most of their users are the same.
      • andy99 1 minute ago
        They have to be careful. There’s not a lot that separates the top models anymore. Look at Grok which has almost no market share or credibility because of Musk, Despite being close to the top performance wise they are behind the Chinese models in adoption for example, which themselves are mostly behind the big two because of trust. It would not be hard to push users away, especially if a less unpalatable player ever emerged.
  • philipwhiuk 22 minutes ago
    Is a new benchmark that useful if existing model improvements are being reflected linearly? Don't we want a benchmark that we aren't seeing much progress in.
  • fractorial 17 minutes ago
    I would love for someone to give me a coherent argument as to how this isn’t tone-deaf, vacuous garbage.
  • crossthestreams 36 minutes ago
    New Trust Me Bro benchmark just dropped
    • Scribbd 30 minutes ago
      And surprise! We are leading!
  • 0x70run 31 minutes ago
    masters at sucking their own d**k