You Can't Claim Models Are Good Enough to Skip Code Review: HamelHusain RT
HamelHusain · x · 2026-08-26
HamelHusain retweets dexhorthy's argument: you can't claim 'the models are good enough that I don't have to read the code' because without reading it, you can't know how much slop is getting in. They bring in @0xblacklight and @vaibcode for discussion.
More from coding & agent
- Perplexity Launches Portable Computer: Fully Local Runtime on NVIDIA DGX — inductionheads · 2026-08-26
- Cisco Launches Cloud Control GA, Introduces AgenticOps Model — aminkarbasi · 2026-08-26
- MIT Professor Demonstrates End-to-End Agent Workflow from Image Inference to Physical Manufacturing — ProfBuehlerMIT · 2026-08-26
- Dev Stack Evolution: From CLI to Web Multiplayer Agent Sessions — steipete · 2026-08-26
- Comet releases Opik, an open-source LLM observability platform — dl_weekly · 2026-08-26
- MEGA launches engineering course for building production-ready AI agents — johnlindquist · 2026-08-26