AI news for platform & agent engineers
Ranked signal · finite reading
One shared ranking. Scan what changed, save what matters, and stop when the finish line appears.
Loading...
OpenWiki generates and maintains codebase documentation so coding agents can find the repo context they need without loading everything into one instruction file. Context & related coverage →
Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a new... Context & related coverage →
Recursive language models (RLMs) fix context rot by having agents write code that dispatches subagents over context chunks instead of pumping everything in one context window. Deep Agents now implements this through d... Context & related coverage →
Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities. By default these attempts are generated independently, wasting inf... Context & related coverage →
Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and offi... Context & related coverage →
I saw Geoffrey Litt speak at AIE yesterday, and one framing he used particularly resonated with me: Understand to participate Geoffrey was talking about the challenge of collaborating with coding agents as they constr... Context & related coverage →
The Vercel Chief of Software explains how its agent framework, eve, was created — and why skills, sandboxes and agent-readable websites now matter. Context & related coverage →
Cassie Shum discusses the architectural evolution of GraphRAG and why data foundations are critical for advanced AI workflows. She explains how traditional vector RAG falls short when addressing global context, multi-... Context & related coverage →
Apple chose Google Cloud to run Private Cloud Compute outside its own data centers for the first time, using NVIDIA Blackwell GPUs, Intel TDX, and Google's Titan chip. Apple maintains an independent append-only hardwa... Context & related coverage →
Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first · Fixed SSL certificate errors (TLS-inspecting proxies, missing NODE_EXTRA_CA_CERTS , expired cer... Context & related coverage →