A Complete Guide to Fine-tuning LLMs in 20 mins! Learn to: • Choose the correct model & training method (LoRA, FFT, GRPO) • Build Datasets & Chat templates • Train with Unsloth notebooks • Run & deploy your LLM in llama.cpp, Ollama & Open WebUI Docs: docs.unsloth.ai

bitchat? now on the App Store: apps.apple.com/us/app/bitchat…

Let your wearable data "speak" for itself! Introducing SensorLM, a family of sensor-language foundation models trained on ~60 million hours of data, enabling robust wearable data understanding with natural language. → goo.gle/4lSLwQi

Polars 1.32 is out and it lands a lot! Let's go through a few: 1/4 Selectors are now implemented in Rust and we can finally select arbitrary nested types:

Dynamic control trained at SUSTech’s ACT Lab in Shenzhen.

anthropic.com/engineering/ef…

Introducing Nested Learning: A new ML paradigm for continual learning that views models as nested optimization problems to enhance long context processing. Our proof-of-concept model, Hope, shows improved performance in language modeling. Learn more: goo.gle/47LJrzI

philschmid.de/agentic-pattern

Vector search: fast, accurate, or affordable. Pick... all three? ✨ Most engineering teams are trapped in an expensive cycle: as their AI applications scale, they're forced to choose between performance and budget. More data means bigger infrastructure bills, slower searches,

The original PPO-based RLHF pipeline had 4 model copies: 1. Policy 2. Reference 3. Critic 4. Reward Model Recent GRPO-based RLVR pipelines have eliminated all of these models except for the policy. - The critic is no longer needed because values are estimated from group

x.com/i/article/2002…

x.com/i/article/2011…

x.com/i/article/2011…

x.com/i/article/2027…

I (finally) put together a new LLM Architecture Gallery that collects the architecture figures all in one place! sebastianraschka.com/llm-architectu…

A Scientist's View of War youtu.be/XI9NG068TwI?si… via YouTube

Really great writeup

how autoresearch works, simplified it's a pattern that lets AI agents run experiments and improve anything you can measure three files is all you need, everyone should be running it. ↓ > program. md is where you tell the agent what to do. your goal, the rules it has to

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating

we just shipped support for subagents with `deepagents deploy`! add an agents/ dir to your project with an AGENTS.md per specialized subagent. subagents are great for task delegation with isolated/optimized context docs.langchain.com/oss/python/dee…