News for hackers. Stuff that matters.
Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by bombcar on Thursday October 29, 2026 @12:35AM (#50284612)
They very aggressively compact when the cache is about to expire, which saves a ton of tokens, the equivalent of doing a handoff at 25% or less.
Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by adastra22 on Thursday October 29, 2026 @12:37AM (#50284625)
I assume that is only if compact is turned on? I never use compaction.
Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by SyneRyder on Thursday October 29, 2026 @01:09AM (#50284786)
They enabled it for everyone in a recent Claude Code update, but you can turn it off (I did).

I am definitely getting frustrated with a lot of the changes they keep making in Claude Code. It's one thing to find settings have changed during your next interactive session, it's another when it changes how overnight unattended sessions behave. I really should be spending more time building my own harness again.

Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by Matticus_Rex on Thursday October 29, 2026 @01:12AM (#50284803)
Check your idleCompaction line in /config to make sure it's off -- several times they've toggled new features on by default for me. This one isn't in the VS Code extension so I don't know if it shipped default-on.
Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by Silagi on Thursday October 29, 2026 @08:43AM (#50288037)
Can I ask why? The modern models deal with compaction remarkably well, to the point where I dropped my autocompact from 1M to 350k. I've seen no change in efficacy and a reduced usage rate.
Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by bombcar on Thursday October 29, 2026 @09:28AM (#50288710)
For certain workloads compaction is great, for others you're better off manually doing a /handoff (or a similar skill you write yourself to keep what you need, toss what you don't; Claude is not always good at figuring it out).

Read your memory.md to see what Claude thinks is very important.

Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by Silagi on Thursday October 29, 2026 @09:36AM (#50288817)
That was my experience in the Opus 4.5 - 4.7 era, but recently it's been on the nose with what I want it to carry over, or close enough that a full handoff would be more expensive than just letting it find what it needs again.

I'm mostly working on moderately sized rust codebases (600k~ lines) with reasonably long running tasks. The only time I intentionally do a handoff is if the next goal is in an entirely different section of the code, or I let the session cache expire, or I'm working with 6.1 Sol for more than a few hours, which admittedly has some horrendous context drift compared to Opus.

Re:Claude Code burns ~15–20% of your tokens on a 3-word stat... by adastra22 on Thursday October 29, 2026 @12:49PM (#50292074)
I have never once had it work for me. Usually it feels like the model got a lobotomy. If I'm working with the model in a chat interface, I feel like we only really start to groove around 500k or so, at which point it knows my quirks and style, and is interpreting my intent correctly. That never, in my experience, survives compaction.

Maybe things are better now. It's been a while since I've compacted a conversation.