News for hackers. Stuff that matters.
Re:Heretic: Automatic censorship removal for language models by selfhoster11 on Monday November 17, 2025 @06:29AM (#45952692)
o3 and GPT-5 will unthinkingly default to the "exposing a reasoning model's raw CoT means that the model is malfunctioning" stance, because it's in OpenAI's interest to de-normalise providing this information in API responses.

Not only do they quote specious arguments like "API users do not want to see this because it's confusing/upsetting", "it might output copyrighted content in the reasoning" or "it could result in disclosure of PII" (which are patently false in practice) as disinformation, they will outright poison downstream models' attitudes with these statements in synthetic datasets unless one does heavy filtering.

There are no comments on this comment yet.