Ask HN: How are thinking efforts implemented?

26 points by simianwords a day ago

Claude and ChatGPT have thinking efforts where you can tune the amount of thinking allowed.

Like low, medium, high, xhigh and so on.

But are they different models underneath? Or same model with different parameter?

The reason I ask is because, if I change the effort param mid conversation in Claude code, I get a warning suggesting I’m breaking the cache.

I don’t think this happens in Codex because when I change the effort, the responses are still quick.

pyentropy a day ago

Take a look at the harmony repo which specifies the internal OpenAI format - the effort level is specified in the context after the <|start|> tag - https://github.com/openai/harmony

Note that inference libs also have parsers that put hard limits on reasoning tokens with separate counters (similar to how you can put a limit on token generation per completion versus waiting for an <eos>). For that, take a look at vllm reasoning docs.

  • pyentropy a day ago

    Examples with inference of different reasoning effort levels is in the OpenAI docs as well - https://developers.openai.com/cookbook/articles/openai-harmo...

    https://docs.vllm.ai/en/latest/features/reasoning_outputs/#a...

    https://developers.openai.com/api/docs/guides/reasoning

    • simianwords a day ago

      I think you have the right answer but I'm struggling to understand: does changing the effort change the prompt at the start of the conversation? I wonder why come up with this way at all? Why not just add a parameter at the end or something? At least it won't break cache.

      Maybe like: add a secret suffix to your chat in the conversation to think more like

         conversation....

   Hey please help
   [think more]
      • pyentropy 21 hours ago

        I'm considering the possibility that it's good to break the prefix and cache because the LLM itself was rewarded (during post-training) with different prefixes/system prompts, each containing reasoning traces of the correct size.

        I might be very very wrong though and LLMs disagree with me, insisting that cache is preserved and the system message doesn't have to change (even though it often contains effort level in context) if effort level changes across turns, and that all you have to do is tell the inference lib that parses think tags to early-close think tags that are too long.

        • simianwords 12 hours ago

          This seems correct but again I would like to think post training could have been also done by checking only the string in the last message sent.

aabdi a day ago

Different models do slight variants.

Usually it’s done in post training to enforce behavior based on prompt. Ie. System prompt with thinking:max or low or wtv.

Enforcement then goes via constrained decoding, checking for think token start and end with max lengths, or other variations

__patchbit__ a day ago

At a guess. May be associated with token length context window. Down selecting is consistent with warning message, forcing cutoff to context window. The technical term cache being a synonym. Increasing the headroom for more "thinking" should allow the implementation to access more resources without warning about the cache breaking.

sometimelurker a day ago

they use multitoken prediction behind the scenes, that might interact with the CoT in a strange way. maybe for different thinking modes they have different MTP models? if so thats interesting

  • pyentropy a day ago

    The number of tokens you predict at time (multi or not) has nothing to do with whether the model wants to emit any, some or a lot of reasoning tokens in reasoning tag -- similar to how branch prediction will not really change the for loop iteration count.

    • sometimelurker 18 hours ago

      no it might. a high reasoning task is probably harder than a low reasoning task, so the same MTP LLM will predict more correct tokens on the low reasoning task. to compensate for this, big labs likely have different MTP LLMs for different cases. it would make sense for them to do this

bjourne a day ago

LLMs work by generating the most likely continuation to a prompt. But they can also generate multiple likely continuations. This create multiple branches which in turn can generate even more branches. The LLM can then evaluate the branches, prune the unpromising ones, and merge the best ones. More branches means more tokens, means more effort.