W&B Exec on Fully Automated Agent Development
thursdai_pod · x · 2026-07-13
In this session, Zubin Aysola from W&B shares a massive shift in his workflow: he hasn't written a single line of code by hand for 8 months, yet his output is higher than ever.
The core idea is that agents are pushing humans up a level of abstraction—"Everybody gets to move up that stack." However, he also highlights a critical question: what happens when you let agents run completely unsupervised? This means that while efficiency skyrockets, reliability and control will become inevitable trade-offs.
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22