LLMS

Language Models Acquire Reasoning Through Reinforcement Learning Training

By

–

20 February 2026 14h43

The models will acquire some amount of verbal reasoning just from the language modelling objective. But reinforcement learning training that specifically targets reasoning paths does give you something quite different.

Gemini models reasoning behavior and objective function optimization

By

–

20 February 2026 14h40

This gets tricky and I'll have trouble answering well in non-premium tweets. If you use a Gemini model and turn off the reasoning, it will 'reason' in the output space instead if you let it. What matters is the objective function and the training protocol

Reasoning models use language computation to overcome step problems

By

–

20 February 2026 14h24

I definitely agree there's lots of problems at that step. I think reasoning models actually have a way around it to some extent though, because they can perform computation in language:

Spatial Reasoning Limitations in ASCII Board Games

By

–

20 February 2026 14h19

My guess is it's not very good at reasoning spatially within ascii representations, or at coming up with better formats. You could try telling it to always look two moves ahead or something. Does it draw boards in its reasoning?

→ View original post on X — @ingliguori

LCMs: A New Cognitive Layer Beyond Token Prediction

By

@ingliguori

–

20 February 2026 14h17

LLMs predict tokens.
LCMs reason in concepts. That’s the shift. Language-agnostic meaning → better abstraction, longer context, less repetition. If it works, this isn’t an upgrade.
It’s a new cognitive layer for AI.

→ View original post on X — @metuk_

Export your data and transfer to another LLM

By

@metuk_

–

20 February 2026 12h12

But you can. Check settings – Data – Export Data. You can also export said data as a zip file and upload to the memory of another LLM

→ View original post on X — @elonmusk

Grok’s mission: truth, beauty, humanity, physics, technology, stars, love

By

@elonmusk

–

20 February 2026 11h53

From this goal of Grok, all things flow: Rigorous truth-seeking Appreciation of beauty Fostering humanity Discovering all physics Inventing all useful technologies Consciousness to the stars Love

→ View original post on X — @pmddomingos

The AI-driven Cambrian explosion in software development

By

@pmddomingos

–

20 February 2026 7h17

Picture the Cambrian explosion in software when it no longer has to be written by software engineers.

→ View original post on X — @bilawalsidhu

Leveraging domain expertise to guide AI models effectively

By

@bilawalsidhu

–

20 February 2026 6h32

Yup. And if you have domain expertise you can really steer these models towards the right solutions w/o sweating the implementation. Really fucking fun