IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
279 articles
11 Sep 2026 · 4 min read
agentic coding
Inception Labs shipped Mercury 2.5 on September 8, hitting 1,107 tok/s on standard NVIDIA GPUs — 10x a typical autoregressive model — by generating text like image diffusion instead of one token at a time. What that means for latency-bound agent architectures.
Read more11 Sep 2026 · 4 min read
agents
OpenAI opened its Agents API in public beta on September 10 — putting the same session, sandbox, and subagent machinery that runs Codex behind one API call. A technical lead's take on what this replaces in your stack and what it doesn't.
Read more10 Sep 2026 · 5 min read
agentic coding
OpenAI says an internal model coordinated 10,000 agents for 88 hours to solve the Navier-Stokes Millennium Prize problem — then a mathematician accused it of building on unpublished work it had access to. A technical lead's take on the swarm-scale mechanics and the attribution problem every AI-assisted team will eventually hit.
Read more10 Sep 2026 · 6 min read
agentic coding
Design agency Wavespace's 'Beyond the Chatbox' framework reframes agent UX around generative UI — tables, forms, and wizards the agent renders on demand instead of a wall of text. A technical lead's breakdown of the pattern, the implementation stack, and a real case study showing 38% faster task completion.
Read more09 Sep 2026 · 5 min read
ai
HydraFusion picks a per-task execution plan across model providers — cascade, critique, or single-shot — and reportedly beats Claude Opus 5 quality on TerminalBench 2.1 at 36-67% lower cost. A Tech Lead's read on whether this replaces your model-routing logic or just moves it.
Read more09 Sep 2026 · 5 min read
agentic-ai
Anthropic's September Claude Code update quietly raised bashOutputMaxChars and taskOutputMaxChars to 128K and added a file-based subagent system prompt flag. A Tech Lead's read on why this unglamorous change matters more than most model announcements for anyone running fan-out subagent pipelines.
Read more09 Sep 2026 · 4 min read
ai
The PyTorch Foundation added Alibaba Cloud and Cambricon as Platinum members (with governing board seats) and Ant Group as Gold at PyTorch Conference China. A Tech Lead's read on what non-CUDA silicon getting a direct vote in PyTorch's roadmap means for anyone betting on the framework's neutrality.
Read more09 Sep 2026 · 5 min read
ai
Anthropic's Claude produced a 13M-line, fully machine-verified Lean proof of Fermat's Last Theorem in 11 days via the open-source Prove2Me orchestrator. A Tech Lead's read on what the multi-agent coordination pattern behind it means for any team building long-horizon autonomous agents.
Read more07 Sep 2026 · 5 min read
adoption
OpenAI's internal per-researcher AI spend sat near zero through February 2026, then rocketed to roughly $600/day by late August — not from a mandate, but from a model that finally cleared the adoption bar. A Tech Lead's read on what the curve shape means for your own rollout.
Read more
