How to Beat GRPO Without Touching Model Weights
Berkeley beat GRPO by 10 points with 35× fewer rollouts and no GPU training,
Lire
Two Skills to Fix the Context Gap in Claude Code
They cover what CLAUDE.md never will.
Lire
![[Hands-on] Build OpenClaw’s Core In a Single Visual Workflow](https://substackcdn.com/image/fetch/$s_!XTyH!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff12abefe-c5e0-4917-b785-07fc46207b64_1376x768.jpeg)
[Hands-on] Build OpenClaw’s Core In a Single Visual Workflow
...using 100% open-source stack!
Lire
Who Actually Builds AI Image Models (and Who Builds on Top)
The 2026 AI Image generation landscape.
Lire
How Top AI Labs Are Building RL Agents in 2026
The era of not writing custom reward functions.
Lire
8 Techniques to Generate Better LLM Outputs
...explained visually with usage.
Lire
Top AI Labs Share an Agent Memory Trick Most Miss
...Microsoft, Google, Meta all do it.
Lire
Claude Opus 4.7 Isn't a Drop-in Replacement for 4.6
The new xhigh effort level and adaptive thinking
Lire
How We Cut Our Claude Code Token Usage 2.8x!
...using Karpathy's context engineering principles!
Lire
72 Techniques to Optimize LLMs in Production
...explained with usage.
Lire
Evolution of Agent Landscape From 2022-26
From weights → context → harness engineering.
Lire
Google solved an Old RNN Problem
A better middle ground between RNNs and Transformers.
Lire