About whether Anthropic's concept-injection experiments show LLMs can introspect on their internal states.
Has this happened?
Yes 12 (11%)Not sure 66 (60%)No 32 (29%)
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
Hacker News has set AI a lot of challenges over the years. Which ones has it met?
About whether Anthropic's concept-injection experiments show LLMs can introspect on their internal states.
Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.
This is causal evidence and already beyond all statistical thresholds as they can trigger this at will.
Their post says:
Even using our best injection protocol, Claude Opus 4.1 only demonstrated this kind of awareness about 20% of the time.
That's not remotely close to "at will".
As I already said, this does incline me towards believing LLMs can be in some sense aware of their own mental state. It's certainly evidence.
Your certitude that it's what's happening, when the researchers' best efforts only yielded a twenty percent success rate, seems overconfident to me.
If they could in fact produce this at will, then my confidence would be much higher that they've shown LLMs can be self-aware.
...though we still wouldn't have a way to tell when they actually are aware of their internal state, because certainly sometimes they appear not to be.