Kimi K3 Is Already Close to Claude on a Real Coding Task
In my little coding test, Kimi K3 and Claude Fable 5 both completed the same repo-wide coding task and passed the same external evaluator.…
Beitrag lesenAlle Beiträge zu OpenAI Codex
Alles in diesem Archiv, neue Beiträge zuerst.
Chinese Codex API Resellers Have a New Problem
Chinese services sell low-cost Codex API access by putting a layer between customers and a large number of ChatGPT subscriptions. A developer gets one…
Beitrag lesenOpenAI Added 1M Users in a Day. Fable Is Still in Limbo.
OpenAI says Codex and ChatGPT Work went from 6 million to 7 million active users in roughly 24 and a half hours. The number…
Beitrag lesenSonnet 5 Is Dead in the Water
Ignore the token price for a second and look at the run cost. Theo's total-run screenshot shows Claude Sonnet 5 max at $6,015 for…
Beitrag lesenAnthropic Is Hitting a Wall
Anthropic had the developer story every AI lab craved. Claude Code worked. Opus was expensive but worth the splurge. Sonnet was known as the…
Beitrag lesenEnable Image Paste for Claude Code and Codex CLI in the VS Code Terminal
If you run Claude Code or Codex CLI inside the VS Code integrated terminal, image paste often doesn’t work because VS Code grabs Ctrl+V…
Beitrag lesenOpenAI models answer an older prompt instead of the current one
There is a strange failure mode that I have been noticing in OpenAI models: in a longer session, the model can suddenly answer an…
Beitrag lesenHow Codex CLI Flags Actually Work (Full-Auto, Sandbox, and Bypass)
If you use the Codex CLI, you’ve probably seen a few flags that look like they do the same thing: --full-auto, --sandbox, and --dangerously-bypass-approvals-and-sandbox.…
Beitrag lesenBreaking Out of the Codex Sandbox (While Keeping Approval Controls)
If you're using OpenAI's Codex CLI, you might want it to work like Claude Code does by default: able to run powerful commands, but…
Beitrag lesen