... Something that surprised me while building this week: "OpenAI-compatible" is a statement about the API shape, not about how code edits are expressed inside it. Aider does not use tool calls. It sends edits as structured text blocks SEARCH/REPLACE delimiters inside the assistant message. The filename is on the line before the fence, not inside it. Cline and Continue use proper tool calls. A response from some backends carries both. The adapter we shipped this week (`openai_ chat.py ... ... LineageLens proxy) handles all three patterns: tool-call edits, text-content edits (Aider

... could look back and see how their thoughts evolved, which felt more meaningful than numbers. This approach aligned well with users who wanted reflection, not performance metrics. User Personas That Actually Shaped Decisions Two personas influenced the design heavily. Aiden Startup Founder (42, Toronto) Aiden

... like button. Benchmarks, benchmarks, benchmarks Benchmarks should always be taken with a grain of salt . They are effectively a snapshot of a models capabilities under near perfect conditions. Sort of like the Big Mac you see on the ads vs the Big Mac you get in the bag. It gives you a good idea, but they're far from a perfect measure of real world usage. Math (AIME 2025, no tools): 94.6 percent Real-world coding (SWE-bench Verified ... ... percent Multilingual programming (Aider