@jxmnop

–

31 July 2025 23h05

no, because it's KL measured on the RL outputs

Scaling Prompt Optimization: Systems, Theory, and Benchmarks Needed

By

–

31 July 2025 22h12

probably 10x more people should be working on prompt optimization systems (we need a vLLM for promptopt), theory, new techniques, benchmarks. the whole kit and caboodle

Model Merging as Compromise for AI Stacking Capabilities

By

–

31 July 2025 20h03

for stacking capabilities it makes sense in this case model merging is an odd compromise

Pretraining Data and Gradient-Matching Training Approaches

By

–

31 July 2025 19h01

oh cool, is it *pretraining* data? and they do the same gradient-matching thing? i wonder what the advantage is over just mixing in and doing supervised training on a few examples every now and again

RLHF Training: Avoiding Model Drift Through Gradient Mixing

By

–

31 July 2025 18h51

here's some free alpha: if we do RL for too long after pretraining, we will surely overwrite parameters and start to forget things in the original instructGPT paper, their best model mixed RLHF with pretraining gradients to avoid exactly this model drift issue yet no one is

Reasoning Model Generalization: Math to Creative Writing Transfer

By

–

31 July 2025 17h45

i'm looking for good examples of reasoning model generalization for example, a model incentivized via RL to think for a while and solve math problems gets better at creative writing is this common?

Prompt Length Limitations for Question Conditioning

By

–

31 July 2025 3h36

the prompt doesn't condition on the question. and it has bounded length. so too short to contain all possible questions.

Models achieving gold without reinforcement learning through prompt engineering

By

–

31 July 2025 3h24

this seems really important: it is totally plausible that a model could get IMO gold without *any* reinforcement learning, given a perfectly-crafted prompt we just don't know, and lack tools to efficiently search through prompt space. glad to see at least someone is trying

Software and Hardware Performance Improvements Over Time

By

–

31 July 2025 0h45

people talk a lot about how software has gotten worse over time (‘enshittification’) but my experience on the whole has been the opposite. things seem to get slowly and consistently better: – neither my phone nor my laptop ever lags. not ever
– the internet is faster