News for hackers. Stuff that matters.
Re:Opus 4.7 to 4.6 Inflation is ~45% by KronisLV on Sunday April 19, 2026 @08:09AM (#47823728)
> This is key. In my experience, asking an LLM why it did something is usually pointless. In a subsequent round, it generally can't meaningfully introspect on its prior internal state, so it's just referring to the session transcript and extrapolating a plausible sounding answer based on its training data of how LLMs typically work.

Yep, I've gotten used to treating the model output as a finished, self-contained thing.

If it needs to be explained, the model will be good at that, if it has an issue, the model will be good at fixing it (and possibly patching any instructions to prevent it in the future). I'm not getting out the actual reason why things happened a certain way, but then again, it's just a token prediction machine and if there's something wrong with my prompt that's not immediately obvious and perhaps doesn't matter that much, I can just run a few sub-agents in a review role and also look for a consensus on any problems that might be found, for the model to then fix.

There are no comments on this comment yet.