Code With LLM Updates

Models are updating so frequently now: Opus 5.5, GPT-6 Sol and Luna, MiMo-V2.6, Grok 4.7, and Step 5 Preview.

omp (oh-my-pi) — a Pi fork by Mario Zechner, rewritten for a real development workflow: sessions, subagents, slash commands, extensions.

The usual git status run at agent startup executes a command from within the repository itself.

OpenHands went from agent to platform over agents in six months OpenHands from agent to coordinator https://www.openhands.dev/blog/introducing-agent-canvas https://docs.openhands.dev/openhands/usage/agent-canvas/acp-agents Previously OpenHands itself was…

Memory in Grok Build, Zen vs third-party harnesses, a completely different Jev, and Geiger.

Cline is also building a native Desktop app.

It looks like Google, following Anthropic, is trying to restrict its subscription-plan models to its own harness only, making it harder to use those credentials in third-party AI agents. https://news.ycombinator.com/item?

SOTA parade: GPT-6 Astra, Claude Fable 5.1, Muse Spark 1.3, Gemini 3.8 Flash and the post-train Qwen 3.8 Max 0902.

Official agentic environment from DeepSeek built on the Cordis microkernel.

Changes in model availability.

Vercel and Slack are also entering the coding tools market. fx — a tiny native code agent https://fx.sh/ https://github.com/vercel-labs/fx fx — Vercel Labs' answer to bloated agentic TUIs — is for now an experimental CLI harness written in Zig: a 6–8 MB b…

A week of minor updates: Grok 4.6, Gemini 3.7 Flash, DeepSeek V4-Pro 0813, GLM-5.3, Qwen 3.8 27B, MAI-Code 1.1 Flash, and Muse Glimmer—all have improved code generation capabilities without changes to their underlying architecture.

Google has strengthened its Flash lineup, DeepSeek has officially released V4 Flash with significantly improved agentic capabilities, Meta has entered the code-agent space with Muse, and Alibaba has updated Qwen Max.

For several months now, new models have been able to operate autonomously for hours and generate rather complex projects.

Open-source skills for controlling AI https://github.com/mattpocock/skills These Skills turn AI from an “improvising assistant” into a controlled engineering tool.

Kimi K3 has became so popular that the company has closed registration for new subscription plans.

The Grok scandal involving "silent" code uploads, followed by open-sourcing as an attempt to regain trust.

Finally, model announcements that represent a meaningful step forward.

Finally, an answer to Claude Code and Codex from Elon Musk's team.

Over the past six months, most new large language models have evolved beyond merely providing high-quality answers; they now possess the capability for sustained, autonomous operation.

Cursor hosted Compile 26, its developer-focused event dedicated to the future of programming. https://www.marketwatch.com/story/social-media-declared-cursor-dead-then-spacex-handed-the-ai-startup-a-60-billion-lifeline-50454e29 At Compile, Michael Truell s…

It seems China is actively expanding not only into models but also into complete coding harnesses / agent apps.

OpenAI News.

Chinese AI services continue to gradually catch up with their US counterparts.

Code generation quality continues to improve, but the US government is trying to restrict access for others.

Chinese AI giant MiniMax has announced a new generation of M models: M3.

Microsoft presented a series of changes at its May Build 2026, shifting from simple AI assistance toward autonomous agents.