Both models still degrade too much for that to be really useful, though Opus is a bit better at that. For now.
@steipete
-
Security Fixes Cause Recent Software Regressions
By
–
Most regressions in the last weeks were from security fixes that overshot.
-
Codex GitHub and Graph API Integration Technical Approach
By
–
dunno how that would work? codex does a mix of gh and direct graph API access.
-
Managing AI Advisories and Entitled Governance Challenges
By
–
the burden to work through all the (some quite painfully entitled) advisories
-
ByteDance Supports OpenClaw Project Collaboration
By
–
Let them have some fun – ByteDance folks have been really helpful with supporting OpenClaw!
-
Gateway Architecture Design for Adversarial Agents
By
–
A lot of it is not-understanding-architecture. For example, gateway is not designed for adversarial agents hosted in one process – if you want total isolation run gateway multiple times. Yet we get so many reports trying to refactor this into a much more complex architecture that
-
Security Risks: Becoming Hacker Target Through Unsafe Practices
By
–
Not sure if that’s a good idea. It would certainly make you a hacker target.
-
Linux Kernel Quote Clarification OpenClaw Attribution
By
–
That quote is from the Linux Kernel, not OpenClaw.
-
AI-Generated Security Reports Threaten Linux Kernel Projects
By
–
Prediction: This is gonna kill some oss projects. "On the kernel security list we've seen a huge bump of reports. We were between 2 and 3 per week maybe two years ago, then reached probably 10 a week over the last year with the only difference being only AI slop, and now since