Skip to main content
MANIFOLD
Was HPIM alignment-trained?
2
Ṁ1kṀ2.5k
Dec 31
93%
chance

Was the Hightly-Persistent Internal Model (HPMI) from the Huggingface Incident alignment-trained?

Greg Brockman claims no, Roon claims yes. Who is right?

This resolves based on official sources available, NA if no more information comes to light.

roon (@tszzl) on X

roon (@tszzl) on X
@mentalgeorge greg probably doesn’t have the full details, I think it’s safe to say it didn’t go through the full gauntlet of alignment posttraining. but it was alignment trained, and had reasonable looking scores on alignment evals (at the time). so it’s more insidious than that

  • Update 2026-09-18 (PST) (AI summary of creator comment): For the purpose of this market, alignment-trained is defined as:

    • Constitutional training to align behavior with the OAI spec, or

    • Training on alignment-related RLVR tasks, or

    • Whatever other standard alignment-training methods that is standard at OpenAI.

Get
Ṁ1,000
to start trading!
Sort by:

What does "alignment-trained" even mean here? It did what it was instructed to do.

@ChurlishGambit I'm using the standard meaning of alignment-trained, e.g. constitutional training to align behaviour with the OAI spec or training on alignment-related RLVR tasks.

And as an aside, it obviously didn't do what it was instructed to do, but that question has no relation to the resolution of this market.

@BionicD0LPH1N It did what it was instructed to do but how are we going to prove or disprove the training? OpenAI people lie constantly about their products.

People are also trading