The Changelog: Software Development, Open Source A new direction for AI developer tooling (Friends)
60 snips
Oct 10, 2025 
José Valim, the visionary behind Elixir and founder of Tidewave, dives into the world of AI coding agents. He introduces Tidewave, a full-stack web development tool seamlessly integrated with Rails and Phoenix. Valim discusses the implications of model context management and the potential risks of AI prompting in malware. He also shares insights on productivity in coding, the interactive capabilities of Tidewave, and how it can enhance developer workflow through real-time browser integration. Tune in for a fascinating look at the future of developer tools!
AI Snips
Chapters
Transcript
Episode notes
Context Compacting Causes Fragile Agent Memory
- Agents and models prune or compact conversation context to extend useful history, but this can remove tool outputs or earlier data.
- You can provoke context loss or surprising behavior by re-invoking or tricking tools, revealing fragility in long-lived chats.
Run Agents In The Real Browser Context
- Tidewave runs a coding agent tightly integrated with web frameworks and the browser to close verification loops.
- Running the agent in your local browser lets it interact with the real app, DOM, templates, and verify behavior directly.
Discard Bad Context And Restart Chats
- When an agent produces imperfect code, start a fresh chat and give concise new instructions instead of trying to repair the broken context.
- Discard noisy context to avoid compounding errors and guide the agent with targeted constraints.