Thread

1. simianwords · 1789889196 · focus · HN ↗

   Bitter lesson means all these tricks will not be needed in a year or two. Either labs will abstract it in harness or models will become good enough that it can do it by itself

   1. wwizo · 1789893109 · focus · HN ↗

      If implemented correctly these tricks will still work on less expensive models delivering nearly identical value.

      Today, a hefty amount of standard coding tasks can be completed with similar results to gpt astra using terra and a tailored harness around it.

      Also the scale matters. One big, expensive session, with a frontier model paired with a dev-babysitter is ok. But make it a factory (kindergarden: few devs, many parallel streams) and you'll want to follow a strict protocol.

Unofficial Hacker News client; not affiliated with Y Combinator.