Mark Schröder

Mark Schröder’s Shortform

• Mark SchröderMay 18, 2025, 9:37 AM

  4 points

  5

  on: Mark Schröder’s Shortform

  Has anyone done a well executed lesswrong finetune?

  Couldn’t find anything decent and i think this might be a good experiment.

• Mark SchröderMar 10, 2025, 6:54 AM

  3 points

  0

  in reply to: Thane Ruthenis’s comment on: A Bear Case: My Pre­dic­tions Re­gard­ing AI Progress

  Ah great point, regarding the comment you link to:

  • yes, some reward hacking is going on but at least in Claude (which I work with) this is a rare occurrence in daily practice, and usually follows repeated attempts to actually solve the problem.

  • I believe that both Deepseek R1-Zero as well as Grok thinking were RL-trained solely on math and code yet their reasoning seems to generalise somewhat to other domains as well.

  • So, while you’re absolutely right that we can’t do RL directly on the most important outcomes (research progress), I believe there will be significant transfer from what we can do RL on currently.
    
    Would be curious to hear what’s your sense of generalisation from the current narrow RL approaches!
    

• Mark SchröderMar 9, 2025, 5:00 PM

  3 points

  0

  on: A Bear Case: My Pre­dic­tions Re­gard­ing AI Progress

  Why specifically would you expect that RL on coding wouldn’t sufficiently advance coding abilities of LLM‘s to significantly accelerate the search for a better learning algorithm or architecture?

• Mark SchröderFeb 9, 2025, 10:06 AM

  3 points

  0

  in reply to: Nikola Jurkovic’s comment on: nikola’s Shortform

  That seems to imply that:

  • If current levels are around GPT-4.5, the compute increase from GPT-4 would be either 10× or 50×, depending on whether we use a log or linear scaling assumption.

  • The completion of Stargate would then push OpenAI’s compute to around GPT-5.5 levels. However, since other compute expansions (e.g., Azure scaling) are also ongoing, they may reach this level sooner.

  • Recent discussions have suggested that better base models are a key enabler for the current RL approaches, rather than major changes in RL architecture itself. This suggests that once the base model shifts from a GPT-4o-scale model to a GPT-5.5-scale model, there could be a strong jump in capabilities.

  • It’s unclear how much of a difference it makes to train the new base model (GPT-5) on reasoning traces from O3/​O4 before applying RL. However, by the time the GPT-5 scale run begins, there will likely be a large corpus of filtered, high-quality reasoning traces, further edited for clarity, that will be incorporated into pretraining.

  • The change to a better base model for RL might enable longer horizon agentic work as an “emergent thing”, combined with superhuman coding skills this might already be quite unsafe.

  • GPT-5’s reasoning abilities may be significantly more domain-specific than prior models.