Nah it’s a user issue. Use /model to switch, it’s not sth the agent can do itself.
@steipete
-
AI Content Moderation: Filtering False Positives and Toxic Behavior
By
–
People say they are false positive, but then I investigate and usually they either use AI or did sth impolite like mass-replying with ads to their stuff. Actual false positives so far were in the single digits. But insult and death threads were filtered and it protects my sanity.
-
OpenAI Subscription: Cost-Effective Alternative for AI Development
By
–
Why not use the OpenAI sub? Way cheaper and supported!
-
Running AI Locally for Better Configuration Management
By
–
It’s far more effective to run AI locally where it can read and edit your config, so we suggest that in the docs instead.
-
MCP Protocol Supports Notification Extension Feature
By
–
it is a normal mcp but also supports the notification extension.
-
Extended GPT 5.2 Sessions and Benchmark Effectiveness Analysis
By
–
I very rarely see a benefit in making such a large block of work. I did had codex sessions going on over 24h back with gpt 5.2 but IMO wrong benchmark
-
Software Engineers Needed for Complex AI Development
By
–
I need software engineers, it’s too complex to just vibe.
-
Using Better Tools Reduces Software Bugs
By
–
imagine using sth that creates fewer bugs in the first place.