News for hackers. Stuff that matters.

A comment on We made Grok 4.5, GPT-5.5, and Claude build the same apps.

Re:We made Grok 4.5, GPT-5.5, and Claude build the same apps by owenbrown on Thursday July 09, 2026 @12:22AM (#48840964)
I’m spending a significant portion of my day waiting for agents to execute.

What’s more interesting to me than time-to-first token or latency is the time it takes for the agent to execute, from starts to finish, excluding when it’s waiting on a human.

[ Parent | on HN ]
Re:We made Grok 4.5, GPT-5.5, and Claude build the same apps by madaxe_again on Thursday July 09, 2026 @02:48AM (#48841870)
Subagents can help enormously…

On which note I recently convinced codex to use the ChatGPT web client to run subagents. Means I only pay for the slavemaster, and all the slaves I can eat for $20 a month. Actually works surprisingly well - I currently have it crunching through a large dataset, which would have taken weeks on a single thread - started last night, nearly done this morning. $20.

[ Parent | on HN ]