Tell me about yourself: LLMs are aware of their learned behaviors · HackerPapers discussions

Tell me about yourself: LLMs are aware of their learned behaviors — mentioned by mapontosevenths

Thu, 12 Feb 2026 21:15:01 GMT

If we equate self awareness with consciousness then yes. Several papers have now shown that SOTA models have self awareness of at least a limited sort. [0][1] As far as I'm aware no one has ever proven that for GPT 2, but the methodology for testing it is available if you're interested. [0]https://arxiv.org/pdf/2501.11120 [1]https://transformer-circuits.pub/2025/introspection/index.ht...

Paper and discussion history. A mention is not an endorsement.

Tell me about yourself: LLMs are aware of their learned behaviors — mentioned by FeepingCreature

Tue, 08 Jul 2025 06:18:09 GMT

Layman warning! But "at sufficient scale", like with learning-to-learn, I'd expect it to pick up largely meta-patterns along with (if not rather than) behavioral habits, especially if the goal is left open, because strategies generalize across goals and thus get reinforcement from every instance of goal pursuit during base training. But also my intuition is that humans are "trained on goals" and then reverse-engineer an explicit goal structure using self-observation and prosaic reasoning. If it works for us, why not the LLMs? edit: Example: https://arxiv.org/abs/2501.11120 "Tell me about…

Paper and discussion history. A mention is not an endorsement.

Tell me about yourself: LLMs are aware of their learned behaviors — HN submission

Fri, 24 Jan 2025 17:44:03 GMT

Tell me about yourself: LLMs are aware of their learned behaviors

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Tell me about yourself: LLMs are aware of their learned behaviors — HN submission

Wed, 22 Jan 2025 14:54:07 GMT

Can LLMs demonstrate behavioral self-awareness?

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.