News for hackers. Stuff that matters.
Re:A Guide to Local Coding Models by lelele on Sunday December 21, 2025 @07:23PM (#46350048)
> With Sonnet, if you aren't clearing the context very often, you'll hit it within a few hours.

Do you mean that users should start a new chat for every new task, to save tokens? Thanks.

Re:A Guide to Local Coding Models by jfreds on Sunday December 21, 2025 @07:37PM (#46350132)
Short answer is yes. Not only is it more token-friendly and potentially lower latency, it also prevents weird context issues like forgetting Rules, compacting your conversation and missing relevant details, etc.
Re:A Guide to Local Coding Models by bitexploder on Sunday December 21, 2025 @09:07PM (#46350600)
Yep. I have Claude snapshot to a markdown doc with key points and resume and iterate. Saves so many tokens.
Re:A Guide to Local Coding Models by stuaxo on Monday December 22, 2025 @05:08AM (#46352796)
Yes, it also helps keep it focused.