@jxmnop: nothing against pangram, but you guys do realise you could just hook codex up to the pangram api and have it keep rewri…
Summary
A user comments that you could hook Codex up to the Pangram API to rewrite text until it passes a human evaluation.
View Cached Full Text
Cached at: 07/27/26, 05:45 AM
nothing against pangram, but you guys do realise you could just hook codex up to the pangram api and have it keep rewriting until the eval says it’s fully human, right?
alex fazio (@alxfazio): nothing against pangram, but you guys do realise you could just hook codex up to the pangram api and have it keep rewriting until the eval says it’s fully human, right?
Similar Articles
@jxnlco: https://x.com/jxnlco/status/2057153744630890620
This tweet thread discusses best practices for using the Codex coding agent, focusing on durable threads, voice input, steering, queuing, and its expanding capabilities beyond code generation to full computer workflow automation.
@JinjingLiang: I have the feeling that Codex does a better job reviewing code & debugging when I prompt it in Chinese Need to run more…
A user observes that OpenAI's Codex performs better at code review and debugging when prompted in Chinese, and plans to run further experiments.
@kplikethebird: .@danshipper said to use Codex, so I used Codex to write 9,000+ words on how to use Codex. https://every.to/guides/code…
A detailed guide on using OpenAI's Codex as an operating system for knowledge work, including setup, workflows, and a seven-day starter plan, written using Codex itself.
@justsisyphus: imagine your codex does QA by himself using computer use without manually telling them every fucking time yes that is w…
LazyCodex is a tool that automates QA using AI computer use, allowing developers to set up automated testing without manual intervention.
@jxnlco: jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis https://jxnl.g…
Jason Liu shares his workflow primitives for using Codex effectively, including durable threads, voice input, and steering to extend AI agents beyond coding into knowledge work.