The text in Claude Code’s “Extended Thinking” output
patrickmccanna.net
The text in Claude Code’s “Extended Thinking” output
1–10 of 248 posts
Re: The text in Claude Code’s “Extended Thinking” output
#2Slashdotted.
Re: The text in Claude Code’s “Extended Thinking” output
#3The full thinking logs are also a summary of a thinking process presumably consistent with one necessary to generate the provided answer. Nobody really understands how LLMs think. Thinking logs seem to be accurate, and summary thinking logs seem to be a good summary of the full thinking logs.
If it's useful, it's useful, enjoy. If you aren't comfortable with that, don't use LLMs. You aren't going to get a mathematical proof of your output, just learn to be comfortable with that, or opt out and be a goat farmer.
Re: The text in Claude Code’s “Extended Thinking” output
#4duh.
Computers don’t think they process, those are very different activities.
Re: The text in Claude Code’s “Extended Thinking” output
#5no way, the contents of "reasoning_summary" are summarized?
fyi openai does the same; not really surprising or particularly evil
Re: The text in Claude Code’s “Extended Thinking” output
#6When you have no moat, you have to try and find desperate ways to manufacture one.
Re: The text in Claude Code’s “Extended Thinking” output
#7It’s not surprising than the Sota model makers core goal is to get user dependent while denying them increasing amounts of understanding of how it works to form a deeply unhealthy dependency.
Tell me this. If you hired a junior engineer or designer who refused to explain their thinking on their code and how they solved for the spec what would you do?
(That being said the reasoning output is still a summary of the Kvcache)
Re: The text in Claude Code’s “Extended Thinking” output
#8When you have no moat, you have to try and find desperate ways to manufacture one.
wdym?
Re: The text in Claude Code’s “Extended Thinking” output
#9When you have no moat, you have to try and find desperate ways to manufacture one.
wdym?
Re: The text in Claude Code’s “Extended Thinking” output
#10The full thinking logs are also a summary of a thinking process presumably consistent with one necessary to generate the provided answer. Nobody really understands how LLMs think. Thinking logs seem to be accurate, and summary thinking logs seem to be a good summary of the full thinking logs. If it's useful, it's useful, enjoy. If you aren't comfortable with that, don't use LLMs. You aren't going to get a mathematica…
I want to measure performance drift over time.
Having access to the reasoning text and output would help with performance measurement.