Francis Greenleaf
@inferencetoken
growing @cline 🇺🇸 ( ͡° ͜ʖ ͡°)
Cursor playing checkers, @cline playing chess.
Here's why we decided to (1) make Cline open source and (2) not make inference reselling part of our business model: When you control the inference (the AI model calls) and we build the harness (the system directing those calls), neither party can obscure what's happening. You…
Let me reiterate this: Cline is THE open source benchmark for agentic code generation performance.
I'd like to point out that for the real world tasks (not benchmarks), Kimi K2 outperforms Gemini. This is telemetry across all @cline users, showing diff edit failure rate. Notice how Kimi has about a 6% failure rate, which is significantly better than Gemini's ~ 10% error…
This Great Tightening has dampened the ‘Aha Moment’ of agentic coding for many users of many promising products. There are physical (compute) restraints that the big model labs and code generation tools are coming up against right now. I’d also argue that they’re coming up…
Anthropic tightens usage limits for Claude Code – without telling users | TechCrunch techcrunch.com/2025/07/17/ant…
You have no idea how cool the things that are going on are
Don’t be a pawn
there's this phenomenon happening with AI coding tools. i'm calling it "subscription fog." you have users bragging about getting $3k of inference for $200/month. then suddenly things "feel" off. when the same entity controls both: 1. the inference supply 2. the harness…
Do you think the cursor guys ever made it to the xAI office?
How is this my highest engagement post 😭 you people are sick
Could you stop following me please