[s3p]

Don't get me started on the thinking tokens. Since 2.5P the thinking has been insane. "I'm diving in to the problem", "I'm fully immersed" or "I'm meticulously crafting the answer"

[ceroxylon]

I once saw "now that I've slept on it" in Gemini's CoT... baffling.

[dpkirchner]

Reminds me of Claude's time estimates. Yeah this project isn't actually going to take 12 weeks, Claude, nice try though.

[fHr]

That's wild haha

[dist-epoch]

That's not the real thinking, it's a super summarized view of it.

[foz]

This is part of the reason I don't like to use it. I feel it's hiding things from me, compared to other models that very clearly share what they are thinking.

[dumpsterdiver]

To be fair, considering that the CoT exposed to users is a sanitized summary of the path traversal - one could argue that sanitized CoT is closer to hiding things than simply omitting it entirely.

[raducu]

> Don't get me started on the thinking tokens.

Claude provides nicer explanations, but when it comes to CoT tokens or just prompting the LLM to explain -- I'm very skeptical of the truthfulness of it.

Not because the LLM lies, but because humans do that also -- when asked how the figured something, they'll provide a reasonable sounding chain of thought, but it's not how they figured it out.