11–20 of 46 posts
From March last year: https://transformer-circuits.pub/2025/attribution-graphs/bio...
There's no reason to believe the model's self-reported "thinking" bears any relation to the mechanics by which it arrived at some output.
Earlier quoted context omitted.
Natural intelligences do this too
No they don't, human intelligence has the ability to form an internal model of itself, which allows it to "notice" its own mistakes and change.
Earlier quoted context omitted.
Natural intelligences do this too
Must we always see this restated every time? It's getting a bit stale always seeing these kinds of comments on articles about LLM.
Earlier quoted context omitted.
No they don't, human intelligence has the ability to form an internal model of itself, which allows it to "notice" its own mistakes and change.
Many who watched the last decade knows just because its possible to noticed mistakes and change, its clearly not a reliable process.
I thought this was already widely known? From March last year: https://transformer-circuits.pub/2025/attribution-graphs/bio... There's no reason to believe the model's self-reported "thinking" bears any relation to the mechanics by which it arrived at some output.
It is annoying when the bot seems be “reasoning” correctly and then makes an obvious mistake at the end. And perplexing when it seems to be completely wrong and then pull the right answer out of a magic hat at the end.
I guess it makes sense; the “reasoning” steps aren’t actually doing logic, just adding more context to influence the final generation, right? But it is weird to see.
Earlier quoted context omitted.
Many who watched the last decade knows just because its possible to noticed mistakes and change, its clearly not a reliable process.
The current political climate is well reasoned and intentional. It might not be yours or mine, however the system is working exactly as the ones paying for it have intended.