if you go beyond the 256k context window it falls off quite a bit yeah, but default limits that.
@steipete
-
Replace Krill with Local AI Solution for Better Performance
By
–
No, use a local AI, it's far more effective. We need to remove krill. It's sub-par compared to local AI.
-
CodexBar Beta Launches Experimental Multi-Account Support
By
–
New CodexBar beta has experimental multi-acount support for codex.
-
Codex /fast reduces need for multiple terminals
By
–
With /fast you don't need so many terminals anymore. This was from a time where codex was half as fast as it is these days.
-
Engineering Team Merges 400 Pull Requests Weekly
By
–
We merge an average of 400 PRs/week, so not quite true.
-
Bug Report: Test Main Branch for MCP Fixes
By
–
sounds like a bug, test main first. bunch of mcp fixes landed there
-
Open Source Maintainer Struggles with AI Agent Adoption Gap
By
–
You don’t realize how hard this is. I have over 40 maintainers now and still ship over 70% of commits. Gap with agentic use is very high.
-
Paid APIs and Plugin Customization for AI Model Providers
By
–
clearly a troll. only paid APIs are model providers. There’s ~50+ plugins you can enable/disable to make it yours.
-
NVIDIA Team Hardens AI Security Against Advisory Overload
By
–
We have a whole team from @nvidia helping sifting through the onslaught of slop AI security advisories (and the occasional important ones) and harden in every release.