alt Hacker NewsGemini last models: temperature, top_p, and top_k are deprecated and ignored
Comments
Possible reasons:
- They might be dynamically adjusting these at inference time [1]. For example, start with a low temperature and generate samples with increasingly high temperatures until one of them passes some quality gate.
- They don't want you to fine-tune on high temperature completions (rejection fine-tuning). You could call this "rejection fine-tuning rejection".
[1] https://rlhfbook.com/c/09-rejection-sampling#related-best-of...
My guess is that RL training being done with particular generation parameters makes models much more brittle to changes in these parameters, and that's why we're seeing changes like this across model providers. But I don't really know.
I'm curious: If someone wanted to serve models off hardware/silicon directly (like Cerebras or Taalas, and soon Google I think) rather than GPUs, would these parameters still be adjustable at request time? Or would they have to decide that before the model can even start serving and it would be locked in until they reload it (which would make it briefly unavailable)?
> To improve determinism, define a system instruction with explicit rules for your specific use case.
"Please be deterministic".
Obligatory "The Conspiracy Against High Temperature Sampling":
https://gist.github.com/Hellisotherpeople/71ba712f9f899adcb0...
> To improve determinism, define a system instruction with explicit rules for your specific use case.
Is this guaranteed to work any better than top_k or top_p? This just sounds like making a smaller version of a Agent.md doc.
fwiw sonnet-5 also drops temperature (sonne-4 had it)
Along with everything else. These parameters can make speculative decoding less accurate increasing the inference cost.
thank god, these parameters are so confusing
1. Sampling parameter deprecation (temperature, top_p, top_k)
temperature, top_p, and top_k are deprecated and ignored. In future model generations, supplying these parameters returns an HTTP 400 error. Remove these parameters from all requests.
Good. These have been basically useless for the past few generations of models, and most of the time made the model perform worst.
[flagged]
> To improve determinism, define a system instruction with explicit rules for your specific use case.
What if I want to do the other thing? When performing research with many sub agents, having a lot of diversity in the hypotheses is a big deal. If my 5 parallel sub agents all produce the same conclusion I might as well have only ran one.
The latest OAI models have done the same thing. I'm currently adding random variation to prompts to compensate for the lack of higher temperature sampling.