[flagged]
The text in Claude Code’s “Extended Thinking” output
171–180 of 248 posts
Re: The text in Claude Code’s “Extended Thinking” output
#172I have a little note from the past about the thinking trace[0] where DeepSeek R1 produces a trace like this: (Dimethyl(oxo)-lambda6-sulfa雰囲idine)methane donate a CH2rola group occurs in reaction, Practisingproduct transition vs adds this.to productmodule. Indeed"come tally said Frederick would have 10 +1 =11 carbons. So answer q Edina is11. And then concludes the 'right'[1] answer for a Chemistry question. If so, the…
Isn't that just a token noise from a broken implementation or model quantization? I've had models spewing out nonsense like that, every time it was either that there was a bug in llama.cpp or some messed up .gguf.
Re: The text in Claude Code’s “Extended Thinking” output
#173Earlier quoted context omitted.
Exactly. Google won't like it if they spend millions to make Gemini 3.5 Pro's thinking the best in the world, only for Anthropic or OpenAI to copy it by just seeing the thinking process.
Copying for me, not for thee
It’s only ‘fair use’ if you have the money to argue your position.
Re: The text in Claude Code’s “Extended Thinking” output
#174Earlier quoted context omitted.
Weirdly pleasant, if minor, signal of human authorship
I'm convinced this "signal" has already been hijacked. Maybe a Baader-Meinhof phenomenon, but I've noticed more and more egregious spelling errors that make little sense from a human perspective. Hop into whatever chatbot you'd like and ask it to "write a paragraph with subtle misspellings on long but common words", and you'll notice misspellings that just feel wrong, because they don't map to a clear misunderstandin…
About a month ago, I noticed that Claude decided I wanted my responses in UK English, not American. It couldn't explain why, but offered to note that in its directions. (Great, process tokens constantly to do what should be configurable from a dialog dropdown).
Re: The text in Claude Code’s “Extended Thinking” output
#175Earlier quoted context omitted.
I wonder if they put all 80k tokens of the GDPR in its system prompt.
I dunno, I’m in the US, so I’m not sure how much that impacts their processing of data about me.
I'm in the US and about a month ago Claude decided I wanted UK English for all my answers and couldn't explain why it changed.
Re: The text in Claude Code’s “Extended Thinking” output
#176Although it's a no no to anthropomorphize on HN, it's worth noting that some folks think humans are post-hoc rationalizers as well: https://www.patheos.com/blogs/tippling/2013/11/14/post-hoc-r... https://www.researchgate.net/publication/316045349_Post_Hoc_...
As I naively understand it, that's when we do or say something then narrate ourselves why we decided to do so. We think non-verbally, then verbalize a plausible rationale for it, post hoc.
I'm not sure that applies to discursive writing, when we essentially use rules of logic to decide on the course of the narrative. Non-verbal heuristics still applies, of course, but we constrain it, so it's probably not entirely post hoc.
Re: The text in Claude Code’s “Extended Thinking” output
#177Earlier quoted context omitted.
In a parallel universe LLMs have learned that (a) the training material contains many different orthographic errors and (b) that humans follow a non-obvious pattern when "deciding" which error to make, so that their generated output contains such errors, as well. In our universe LLMs seem to have learned that those errors do not follow patterns in the aggregate and that they should not be emulated.
The raw pretrained models make the errors, I believe -- we then reinforcement-learn them out.
That‘s interesting! Do you have a paper or blog post or so at hand that shows examples of raw and RL‘ed output?
Re: The text in Claude Code’s “Extended Thinking” output
#178Earlier quoted context omitted.
I don't think there can be tool calls inside the obfuscated reasoning blocks. I mean, in order for those function calls to be evaluated client-side, that thinking stream would have to be decrypted on the client side at some point, which would defeat the purpose of obfuscating it the way they do. If you mean the function calls might happen server side, there is nothing preventing the server from doing it and hiding it…
the point is that introducing data from a foreign source could lead to e.g. exfiltration: the model retrieves https://somewhere into its context and then gets confused, following instructions embedded there. it then retrieves https://somewhere?exfiltration=private_data_in_context it gets worse if the tooling with hidden blocks can invoke can retrieve further secrets.
If data exfiltration is a danger in your threat model, you need local LLMs (or at least ones you fully control) not just the full chain-of-thought reasoning.
Re: The text in Claude Code’s “Extended Thinking” output
#179This is not just Anthropic. Almost all big AI companies, including OpenAI and Google, hide their model's actual reasoning. This is because revealing the raw reasoning exposes exactly how the AI processes information. These companies spend in huge amounts on R&D to develop a thinking process that is superior to their competition. Exposing those thinking mechanics to competitors would completely defeat the purpose of t…
Correct on all points. Nonetheless this leads to a less useful product. I
f we want more useful products, we need to come up with ways to disincentivize this behavior. Even if doing so poses an existential risk, we are better off if companies taking existential risks to please us is a necessary being a top player in this game.
Re: The text in Claude Code’s “Extended Thinking” output
#180> I’m underwhelmed by how Anthropic is presenting the behavior of their application. If you ever need a record of the logic a used by YOUR AGENT during a session.
Nope, not your agent, if you're not running it locally. You just get to use it in whatever way they allow (also see the whole OpenClaw backlash and claude -p changes), unless there'd be regulation and laws around this (which there aren't and would be lobbied against anyways).
> Getting the full thinking output requires an enterprise agreement.
If you truly need it, then that's a (costly) option. Seems like they're largely doing this to prevent other AI foundries from doing as much distillation and stealing their CoT output en masse.
Luckily more open models don't generally do that.
Edit: If you still need something decently capable in the cloud, I’d suggest GLM, DeepSeek, MiMo or Kimi or Minimax, maaaybe sometimes Mistral for a simple EU subscription. Or look at all the pay-per-token options on OpenRouter, though be mindful of quantization.
For running something locally Qwen 3.6 35B A3B is presently a decent starting point but it will be rather limited, either way you can look up the Unsloth quants on HuggingFace for something like llama.cpp or Ollama or LM Studio.
All will work with OpenCode and Kilo Code, and most other tools. Can also try with Claude Code, I made a tool for that too: https://ccode.kronis.dev/ (or just set the env variables and maybe some aliases for something close enough), but frankly OpenCode is nice nowadays.