I made a skill that talks me out of bad business ideas
/business-brainstorm — it runs any idea through a 9-dimension founder filter (problem, wedge, moat, portfolio fit, opportunity cost…), triggers real market research on the unknowns, and gives a verdict: build, sleep on it, or pass.
Watch it kill an idea I was genuinely tempted by — and hand me something better.
Part of Maker Skills — 18 free, open-source skills for founders & operators. Install in Claude Code:
/plugin marketplace add coreyhaines31/makerskills
I was wrong
I've been saying for months that open source AI models are 6 months behind frontier
They caught up. GLM 5.2 is as good as Opus 4.8
This changes everything. If you run GLM 5.2 locally no government can take it away. You become sovereign
And even if you run through APIs, its a fraction of the cost
The battlefield is different now. If open source is as good as frontier, and people have cheaper alternatives, governments can't be as quick to regulate. It will destroy the frontier AI labs
All of this is such a massive win for the people
If you are not paying attention to local models yet, you are making a tremendous mistake
The Cursor Acquisition Survival Kit
10 open-source coding agents to switch to before SpaceX closes the Cursor deal in Q3.
1. Cline
60K+ stars. 80.8% on SWE-bench. Apache 2.0. The #1 open-source VS Code agent in 2026. Bring your own API key. Stay in your editor.
Repo → https://t.co/hjjDVgiRd3
2. Aider
Git-aware terminal agent. Auto-commits clean diffs. The reason indie developers ship 5x faster than full teams.
Repo → https://t.co/67EsCLF7cu
3. https://t.co/EWKShiIYlY
The open-source extension for VS Code and JetBrains. Apache 2.0. Fully customizable. Works with any model, including local Ollama.
Repo → https://t.co/AkKdzpjTv6
4. OpenHands
77.6% on SWE-bench Verified. MIT license. Autonomous coding agent that reads issues, writes code, and ships PRs. Used by engineers at Apple, Google, Amazon, Netflix, and NVIDIA.
Repo → https://t.co/kqap76TDuB
5. Claude Code
LogRocket ranked it #1 AI coding tool in February 2026, ahead of Cursor at #2. From the company building Claude.
Repo → https://t.co/4aqJHI2sTd
6. Zed
Native Rust editor. 0.12 second startup. Real-time multiplayer collaboration. The performance-first answer to Cursor.
Repo → https://t.co/iYSso8s0p1
7. Void Editor
Open-source VS Code fork. MIT licensed. BYOK with any provider. The fastest-growing open IDE alternative.
Repo → https://t.co/FrYHztw2vr
8. Tabby
Self-hosted Copilot alternative. On-prem inference. Zero cloud dependency. The choice for regulated industries.
Repo → https://t.co/1vmF54sUX2
9. Kilo Code
VS Code extension agent. Apache 2.0. The broadest documented provider matrix in the open-source space.
Repo → https://t.co/V39K0VmCi6
10. OpenAI Codex CLI
Terminal-based agentic coding from OpenAI. Apache 2.0. The CLI agent every backend developer keeps installed.
Repo → https://t.co/pQ4ipZkLf0
What's crazy to me is that Fable is blocked from life sciences broadly, nerfed even if you get passed the classifiers and filter level blocks.
The whole point of AGI/ASI is to cure all diseases. Everything else is just nice to haves. But Anthropic wants to close off that path.
I think Anthropic might be the worst company on the planet.
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity.
This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.