Working on codex at big token helped, learned lots of little tricks to make GPT better and updated the claw harness.
@steipete
-
GPT 5.4 Upgrades Testing Available in Dev Channel
By
–
Anyone who wanna help me test the GPT 5.4 🦞upgrades: openclaw update –channel dev ovoDRIZZYxo (@aleks_todo) like butter! hahaha diffrence?? 1h ago i was about to jump out my window. Now its waaaaaaaaaaaaaaay better. GOD MODE — https://nitter.net/aleks_todo/status/2040924672078774520#m
-
Major progress on automated testing with AI assistance
By
–
Not quite at dark factory levels, but that's a big step forward. Brainstormed with codex and it… just works (okay took 6h to build but damn. Way better than old-school e2e tests)
-
New QA Process Using OpenClaw for Self-Testing with Synthetic Messages
By
–
Working on a new QA process where we use openclaw to QA openclaw with a new synthetic message channel. Orchestrator agent understands project, defines tasks (e.g. ask agent to create cron) then verifies that agent did what that. If failure -> spin up subagent to analyze+fix.
-
SDK Usage Debate: CLI Mode and Performance Comparison
By
–
The verdict on SDK use is still out. I'm not seeing a clear allowed/not allowed here. We have a mode that uses the cli, which is allowed. Just… pi is faster than the other stuff out there.
-
Automated AI Content Filtering Cron Job Solution
By
–
I tell ya having a claw cron that just mutes AI slop (and slurs) every 5 min has been GODSEND.
-
Jump Desktop and VNC Setup for Mac Studio Remote Access
By
–
Install Jump Desktop and vnc into a Mac Studio in your office. Yes there's 1000 other "better" ways like tmux but this won for me because it's just sooooo convenient. And your clanker will run no matter what.
-
Legacy Context Risks in AI Agent Development and Coding
By
–
you can't. legacy makes no sense for coding or agentic work. far too risky re prompt injection too.
