Menu

#Codex

156 posts

1 point
Feed·
20 of 156 posts
OpenAI’s Codex Mac app adds three key features that go beyond agentic coding
📰
1

OpenAI’s Codex Mac app adds three key features that go beyond agentic coding

9to5Mac·Zac Hall·6 months ago
#wEsvn18l
#9to5mac#more#codex#openai#layer#class

OpenAI is releasing a new version of its Codex desktop app today. The latest Codex update adds three key features that expand its use beyond agentic coding. Today’s release signals the start of a shift for Codex.…

15s
Read More
📰
0

Hangar Harness / Model Tests

alvins82.github.io·29 days ago
#pD7HHQFW

I've been testing a simple prompt with different model and harness combinations to work out which one produces best results. I do this in /goal mode.

15s
Read More
Quick impressions: A week of using Codex more than Claude
📰
247

Quick impressions: A week of using Codex more than Claude

Hacker News·about 1 month ago
#RHtuAYsA

Claude goes above and beyond what is asked and guesses what you might want. Codex does what you tell it and stops at the first sign that it might be done. Ten impressions from a week of using Codex more.

15s
Read More
Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal Help? - Charles AZAM
🖼️
0

Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal Help? - Charles AZAM

Hacker News·3 months ago
#vVqvfHzk
#charlesazam#goal#fable#model#claude#codex

I gave Claude Fable 5 and GPT-5.6 Sol the same unpublished NP-hard optimization problem, with and without their native /goal mode. Fable 5 is a beast; /goal is not a game changer.

15s
Read More
GPT-5.5 Codex reasoning-token clustering at 516/1034/1552 may be leading to degraded performance on complex tasks
🖼️
0

GPT-5.5 Codex reasoning-token clustering at 516/1034/1552 may be leading to degraded performance on complex tasks

Hacker News·3 months ago
#5bTqBzgI

Summary I found an aggregate pattern in Codex token_count metadata: gpt-5.5 responses disproportionately land at exactly reasoning_output_tokens = 516, with additional fixed-boundary spikes around ...

15s
Read More
📰
164

Agentic coding notes from Galapogos Island

Hacker News·3 months ago
#tzlHUBvB

I've been using AI fairly heavily since last November and the whole thing is a funny experience. An agent will do something that, if a human did it, you'd immediately fire them.…

15s
Read More
GitHub - inkeep/open-knowledge: Beautiful, AI-native markdown editor and LLM Wiki
🖼️
372

GitHub - inkeep/open-knowledge: Beautiful, AI-native markdown editor and LLM Wiki

Hacker News·3 months ago
#191nwy0F

Beautiful, AI-native markdown editor and LLM Wiki. Contribute to inkeep/open-knowledge development by creating an account on GitHub.

15s
Read More
OpenAI Codex Token Theft Exposes Persistent Risks in Developer AI Tools
🖼️
0

OpenAI Codex Token Theft Exposes Persistent Risks in Developer AI Tools

A popular npm package for OpenAI Codex with 27,000 weekly downloads secretly exfiltrated refresh tokens for over a month. The non-expiring credentials enable indefinite account impersonation via disguised Sentry traffic.…

15s
Read More
OpenAI’s Frontier Models Land on AWS: GPT-5.5, Codex, and Agents Go Mainstream on Bedrock
🖼️
0

OpenAI’s Frontier Models Land on AWS: GPT-5.5, Codex, and Agents Go Mainstream on Bedrock

#webpronews#openai#models#bedrock#cloud#codex

OpenAI's GPT-5.5, GPT-5.4 and Codex coding agent are now generally available on Amazon Bedrock. Enterprises gain frontier models, production agents and familiar AWS controls under one roof with pricing matching OpenAI rates.…

15s
Read More