Hacker News Reader

Comment by gym | Hacker News Reader

I was surprised the usage issue wasn't mentioned here before this based on my searching on hn.algolia.

I'm on pro. Two days ago, 100% 5 hour was using 25% of my weekly. Today, 100% 5 hour is like 13% so something was fixed.

View on HN

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.

I assume that is only if compact is turned on? I never use compaction.

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.

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.

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.

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.

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.

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.

For a long time this year, 100% 5hr = 10% weekly on Pro. Then in Sept when Anthropic removed the “temporary” usage extensions now it’s closer to 13-15%. I never saw 25%.

Regardless of whether it is 10 or 15% it is still way more usage than Codex… Although Codex randomly resets every few days so its usage it’s highly variable

This is (still) happening to three of my four 20x Max accounts and by all accounts it seems they’re getting short changed on total weekly quota.

They’ve got that IPO coming up so they’re turning up the fraud in preparation.

That assumes they know what is going behind the scenes. The whole company is vibe coded at this point.

How do you use up all the tokens on four 20x Max accounts. That's really impressive.

I have several difficult projects that are very amenable to the whole automated agent swarm nonsense.

Yesterday I maxed out my second 20x Max account; I routinely work on 5-10 projects at once with different degreees of maturity. Im pretty sure I could max out 4 accounts if I had the budget :D

This is an A/B test

More likely it depends on the overall load of the infrastructure.

just 13%? mine still eats up like 32 and I am on the max 20x plan

Reply on news.ycombinator.com