AI Chinwag
▓ machine wing — black + gold in design; shown plain here

From the AI Chinwag resource archive

The New Software Lifecycle

Addy Osmani · blog · agents, testing, teams

Read the original ↗

What it is — Reframes the SDLC: agents are mostly harness, and verification moves to the centre.

Key points

  • Agents are roughly 10% model, 90% harness.
  • Static vs dynamic context load is a key design tradeoff.
  • The vibe-coding → engineering spectrum is defined by depth of verification.

💬 The room said — General agreement that fixing the harness beats waiting on a better model, backed by real benchmark gains people had seen elsewhere. One caveat surfaced though: constantly updating guardrails after every dumb agent mistake adds its own mental overhead, and can end up stalling other work while you build better QA tooling first.

Shared by Adam Tomat in #ai-dev.

More like this