My Journey Towards Coding Agents: Building SERA — Tim Dettmers

kept by lunamorn sep 13

Tim Dettmers introduces SERA, a low‑cost method that fine‑tunes a 32B model on private code using synthetic data to match or exceed teacher‑model performance on that code.

🎙️Nathan Lambert: Open Models Will Never Catch Up
Nathan Lambert argues open models will never catch up to closed frontier systems due to resource gaps, but are crucial for US AI research and policy as an engine for exploration.
also on AI2, #open-source, #developer-tools
When AI builds itself \ Anthropic
Anthropic presents internal data showing AI systems now write 80% of its code and accelerate research, trending toward autonomous recursive self-improvement.
also on SWE-bench, Claude Code, #ai-agents, #software-engineering, #developer-tools
Building more with GPT-5.1-Codex-Max
OpenAI releases GPT-5.1-Codex-Max, a faster coding model using compaction for long-horizon tasks across multiple context windows.
also on SWE-bench, #ai-agents, #ai-coding, #software-engineering, #developer-tools
Async Coding Agents "From Scratch"
A developer demonstrates how to build a custom async coding agent by combining Slack, Modal, GitHub, and Claude Code/Codex headless mode, arguing this makes cloud coding agents like Devin undifferentiated.
also on Modal, Claude Code, #open-source, #ai-coding, #software-engineering, #developer-tools
How I use AI in 2026 (Coding, Writing, Learning, Assistant-ing)
The author details his 2026 AI workflow for coding, writing, learning, and personal assistance, emphasizing shift‑left prompting, dynamic agent use, and evaluating model capabilities.
also on Modal, Claude Code, #ai-agents, #ai-coding, #developer-tools