The complete reasoning-from-scratch video series is now up (and linked) here: https://magazine.sebastianraschka.com/p/building-reasoning-mod...

Reasoning From Scratch round 8, the finale! This last lecture in the series covers distillation as an efficient alternative to the previous ...

Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format ...

Spontaneous morning chat with Juergen Schmidhuber and Jake Newfield philosophizing about AI. Sry my mic somehow disconnected but Juergen ha...

Reasoning from scratch, round number 6! An introduction (and implementation) of Reinforcement Learning with Verifiable Rewards (RLVR) and G...

Took a while, but here it is, a mega write-up on language models for text classification and, of course, Jev. It's basically a visual guide...

A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a f...

Reasoning from scratch, round number 5! This time, talking about log-probability scoring (also a great fundamental concept for loss function...

The main appeal of open-source agent harnesses isn't that they are free, but that we can inspect what they are doing on our computers.

MiMo-V2.6 is "simply" the best (for now). Despite its simple architecture design it's currently No.1 in the open-weight benchmarks (weighted...

It’s easy to dismiss Jev it as “just a classifier”. But people (me included) who have been training encoder-style models for classification...

Inference scaling part 1. Starting with a modded text generation function (temperature scaling, top-p filtering, multinomial sampling) to ge...

Interesting new insights into the old AdamW vs Muon debate: Muon seems to do better because it reduces memorization. https://twitter.com/Cal...

Some food for thought when designing benchmarks... So, here's a little computer-use (visual) comparison between GPT-5.6 Astra and Qwen3.8 M...

Since I had to discuss the "pacing" with a lot of people this weekend, here are my two cents: I don't think pacing literally means that thes...

Reasoning from scratch round 3: This time, I cover generating a verifier for... a) ...evaluation (base model versus any future model improv...

Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though!...

Nice showcase that interesting LLM work can be done on single GPU! https://twitter.com/gpjt/status/2098129100514689364

I put together a mega write-up on GPT-6 Astra & looped transformers. How looped transformers / recurrent depth works, cost-tradeoffs, wheth...

Re today's incident, maybe not a bad idea to check your settings (Settings → Data Controls)