logoalt Hacker News

CompoundEyestoday at 1:36 AM2 repliesview on HN

Pretty basic. The codex app with one conversation per project and several running simultaneously all hours. I’m going for max caching that way and it never gets lost even with compaction somehow. Each has a plan with milestones to keep up to date and a thin agents file. I check in on them in the Remote app. Use case is protocol and control reverse engineering of audio hardware. I think they must be identifying the heavy use agent sessions and cranking up their cache lives so it’s not a big deal for them.


Replies

childintimetoday at 10:18 AM

I'd like to see a benchmark on this specific topic: Reverse engineer the hardware protocol from a driver, or just migrate a driver from one OS to another.

show 1 reply
rpdillontoday at 1:45 AM

A billion tokens a day is 11,000 tokens a second sustained. How many tokens per second are you getting off of GPT 5.6 Sol per project?

show 2 replies