learning with yacine show

usually post-training with GRPO will straight up collapse the model onto a tight set of potential answers (i.e. the spooky sharpening of the distribution).which in some cases might be exactly what we’re looking to do.however, in the grand 2026, we are increasingly using these models in long running harnesses that requires the LLM to think about different solutions and act on them compositionally to stumble on a discovery.havi...

continual learning is one hell of a hot topic in 2026 and it’s beautiful because (like consciousness) barely anyone agree on what are we even talking about.this is why earlier this year I sat down with Ilija from the prime intellect bunch to discuss what he thinks about the subject while bathing in his radiating enthusiasm!in this 1h30min discussion we are going to talk a whole bunch on how he thinks about the components of c...

this discussion I had with alex earlier this year re-shaped a lot how I’m seeing these new breed of frontier models that are specialist at coding + multi-agent + long running.

the concepts of compositional generalization and sub tasks being locally in-distribution makes it very very obvious why LLM + harness are doing so well right now.

and also explain why tweaking the harness a bit sometime make a whole set of tasks that were...

open models are infinitely interesting to me. being able to peek under the hood and look at the interconnected pieces that each hums and work in a specific way to feed the whole is a blessing.

I had a fantastic time earlier this year chatting with chris about the nemotron family of models and why they are engineered the way they are.

throughout the discussion it became clear all decisions surround nemotron 3 ultra was about making it...

today we are taking a deeper look at of the secret behind LLM pretraining which is synthetic data pipelines with Joel Niklaus machine learning engineer at Hugging Face!joel an his team ran 90 controlled experiments and burned over a trillion tokens to figure out what actually makes good pretraining data and in huggingface fashion provided all of their findings/artifacts openly!

lots of things to learn from experiment like this and t...

sometime there is an idea that just makes other weird research results make so much more sense and sort of cascade to explain a whole bunch of phenomenon.

neural thicket from the great yulu gan is one such paper that I absolutely loved from start to finish.

the old mental model I had for pre-trained neural networked was that the pre-training regime made them land on a single good set of weight that was optimal for many tasks.

but afte...

Benchmarking LLM in 2026 is now a high stake task that requires deep expertise on LLM architecture, Prompt Engineering, Harness, Sandbox, Scoring, Hardware, Serving, and more.

It’s a much different exercise than in the past that have a big impact on the performance of the final model.

Not only that but benchmarking also is starting to have deep cybersecurity concern as frontier models have gained the capabilities of chaining ...

earlier this year I took two of my friends (ludwig and lazarz) on a big ol' discussion on how to leverage ai for learning purposes in general.

what I like about these two lad is that they are their own man. they will say what they think without reserve (hence the many constructive disagreement during the interview).

what I also like is that they have quite different learning background with ludwig being an almost pure hustling self-t...

auto-research is starting to gain traction as a very viable paradigm for creating useful research discovery.now, that paradigm is still in its infancy and the infrastructure to hold all that trail of context as the agents blaze through experiments isn't well defined (to say the least).on that topic, I had the chance to chat with my boys francesco and giulio from paradigma about what underlying infra is needed to make this paradigm ...

I had an awesome time interviewing @IdanShenfeld and @jonashubotter from MIT and ETH Zurich about self-distillation.

this very promising post-training paradigm where the model acts as its own teacher by conditioning on environment feedback or demonstrations.

we cover the SDPO algo for reinforcement learning with rich feedback and SDFT for continual learning without forgetting along with many applications.

we dig into how it works, w...

hey folks first time posting this sort of interview as a podcast (shout out the three anon on twitter that requested it).

now that I think of it the format does make sense since me and the interviewee are mostly chatting and exchanging ideas!

will be posting more of these in the future!

in this episode I had the pleasure of spending not 1 but 2 days interviewing the learning legend justin skycak.

we've talked about his quite impressive...