Re:GitHub Agentic Workflows
by teaearlgraycold on Sunday February 08, 2026 @04:58PM
(#46938962)
Eventually this specific issue will be RLHF’d out of existence. For now that should mostly solve the problem, but these models aren’t perfect at following instructions. Especially when you’re deep into the context window.
> Especially when you’re deep into the context window.
Though that is, at least to me, a bit of an anti-pattern for exactly that reason. I've found it far more successful to blow away the context and restart with a new prompt from the old context instead of having a very long running back-and-forward.
Its better than it was with the latest models, I can have them stick around longer, but it's still a useful pattern to use even with 4.6/5.3
Re:GitHub Agentic Workflows
by teaearlgraycold on Sunday February 08, 2026 @05:24PM
(#46939182)
Opus has also clearly been trained to clear the context fairly often through the plan/code/plan cycle.
Re:GitHub Agentic Workflows
by catlifeonmars on Monday February 09, 2026 @08:29AM
(#46944991)
Is it training, or prompting from the CLI?
When using codex, I usually have something like `Never add 3rd party libraries unless explicitly requested. When adding new libraries, use `cargo add $crate` without specifying the version, so we get the latest version.` and it seems to make this issue not appear at all.