I used to see llama as a base model in most experiments, now qwen has taken over. Diversity in base models in experiments is much much more valuable than any hyperparam tuning or extra runs!

Is there an LLM out there that asks follow-up questions? 😅 Would be my go-to if it exists

Is it still cool to do PPO/DPO or must I do reasoning

On my reading list this week: "the first theoretical result on how to identify the ideal depth for safety alignment... indicating that broader ensembles can compensate for shallower alignments"!!!! arxiv.org/abs/2502.00669

Yes 👍🏼

Does anyone like arxiv html? I immediately switch to the pdf view

gemini is crazy at coding, insanely crazy good

Ever wonder how LLM developers choose their pretraining data? It’s not guesswork— all AI labs create small-scale models as experiments, but the models and their data are rarely shared. DataDecide opens up the process: 1,050 models, 30k checkpoints, 25 datasets & 10 benchmarks 🧵

It is critical for scientific integrity that we trust our measure of progress. The lmarena.ai has become the go-to evaluation for AI progress. Our release today demonstrates the difficulty in maintaining fair evaluations on lmarena.ai, despite best intentions.

@ whoever is on the google ai studio team: please fix the chat history never being saved! i cannot access most of my gemini conversations... and this has been an issue since january 🫤

I judge llms by how bayesian they are #1 gemini 2.5 pro (channeling bayes himself) #2 gpt 5 #3 o3 #4 gpt 4o Please stop the bayesian propaganda