Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Maximizing the value of your Claude Code sessions

claude.com

Post reply on HN
Print view View original

101–110 of 206 posts

Re: Maximizing the value of your Claude Code sessions

#101

Post by crthpl »

radlad wrote: post #48
apt-apt-apt-apt wrote: post #3

I'm finding that unexpected cache rewrites cost me huge. I have 1h cache TTL set, and do nothing to cause rewrite (response in time, no model/effort/tool changes). At 400K tokens in, I'll write a message, and /usage shows only a small increase in cache write. On the next message, cache writes shows 800K, and by the end, I often hit 2M cache writes with no explanation. This seems to happen when: using /btw, asking it…

I have long suspected but not confirmed that /btw uses a lower tier model like Haiku. Depending on how you're triggering reviews, you may be using a sub-agent?

it does not use haiku. you can just ask Claude (possibly not fable BC of cyber) to reverse engineer the obfuscated JS.

Re: Maximizing the value of your Claude Code sessions

#102

Post by crthpl »

mccoyb wrote: post #7
csallen wrote: post #6

Earlier quoted context omitted.

I'm trying to understand your point of view, but it kind of just sounds like you're against learning how to use tools efficiently? I mean, agentic coding software is hardly the first tool to exist where learning some idiosyncrasies of how to use it well can result in more efficiency and cost savings.

It's very easy to understand: - I'm happy to learn how to use tools efficiently - I like to be able to inspect my tools - I'm against tools changing underneath me Are you against any of these points?

what specifically has changed about Claude Code?

Re: Maximizing the value of your Claude Code sessions

#103

Post by jaggederest »

hackernudes wrote: post #53
kristjansson wrote: post #42

Earlier quoted context omitted.

the norms of issue trackers are strongly opposed to “bump”. these autoclose bots may yet change that

In this case there is a two phase staleness check. The bot marks it as stale and it is correct to "bump" it if you think it is still important. The nixpkgs repo works the same way. I think it backs off from adding stale again as it gets bumped. I'm not saying it's a perfect solution but for projects that deal with large amounts of issues it's workable.

They should just utilize the old joke about hiring: immediately throw away half the tickets, because you don't want to work on an unlucky ticket.

It'd save the run around and have the same ultimate effect. Or, we could properly work on tickets instead of making the gate "has enough time to follow up on this 14 days later"

Re: Maximizing the value of your Claude Code sessions

#104

Post by Petersipoi »

docheinestages wrote: post #89

Anthropic should build a harness (and model) that smartly takes care of all these points. Not requiring the user to do the manual work. All I see are excuses because they cannot handle the load and enforce strict quotas on users, all while OpenAI constantly resets their quotas. With Qwen 3.8 27B, we're one step closer to on-device LLMs that can replace subscriptions.

The amount that OpenAI resets their quotas is nuts. It's like, every 2 days I swear. Feels so fucking good. Whenever I think about switching my $200 plan back to Claude for a month I'm reminded that they still have a 5 hour usage limit, which feels so absurd now that I've used Codex for a couple of months.

Re: Maximizing the value of your Claude Code sessions

#105

Post by fg137 »

tolugenius wrote: post #4

Part of the cynic in me just wants to ask "why not make a better harness by default?" The other cynic in me knows I'm about to see a hundred post on 'HOW TO 10X CLAUDE" from the ai bros and I'm already tired. I guess if I had to ask something (as someone who doesn't use CC as their daily driver), how much control do you have on subagents and roughly how do define or know when a session is getting too long? I know the…

> "why not make a better harness by default?"

Especially the /compact part. Like, if a session has been idle for 55 min, why not just automatically run compact at that point?

Re: Maximizing the value of your Claude Code sessions

#106

Post by bmitc »

mccoyb wrote: post #5

I mean, it feels hard not to laugh at this type of blog post. My cynical interpretation is that this is a type of passing the buck to engineers in enterprise settings ("Stop spending tokens. Did you read the value maximization blog post? It is your fault.") Oh yes, Claude will do all sorts of different things -- it depends on how you use it! You should totally learn all of these little finicky things ... because now…

I fully agree. All these blog posts are basically features they should be implementing. They advertise they are replacing software development, but then these tools require a massive amount of overhead akin to having to train new hires. But these tools never actually learn and are not trainable, and Anthropic releases a blog post every six months about how to re-invent your workflow. Even the author of Claude Code just told everyone they should delete all their `CLAUDE.md` and skills every six months.

It's wildly lazy.

Re: Maximizing the value of your Claude Code sessions

#107

Post by hetspookjee »

zmmmmm wrote: post #93

What I want is a version of `/clear` that keeps the conversation but drops out things like bloated logs, error traces, etc that were only relevant in the immediate local context. I guess compacting somewhat does that but I want something more explicitly that trims out these extremely bloated artefacts while maintaining in full the actual conversation history.

Create a skill for this that you can invoke a new session in referencing your previous session id. Your instructions here read clear enough it seems to create it. Though a handover skill with this kind of behaviour in the same session might be more economical given the cache materials is already there.

Re: Maximizing the value of your Claude Code sessions

#109

Post by NamlchakKhandro »

DangitBobby wrote: post #51
mccoyb wrote: post #5

I mean, it feels hard not to laugh at this type of blog post. My cynical interpretation is that this is a type of passing the buck to engineers in enterprise settings ("Stop spending tokens. Did you read the value maximization blog post? It is your fault.") Oh yes, Claude will do all sorts of different things -- it depends on how you use it! You should totally learn all of these little finicky things ... because now…

Not sure how this level of cynicism is even remotely warranted. The post helps people who don't understand LLMs very well get the most out of Claude. Your incentives here are actually aligned with Anthropics since both of you want fewer tokens inputted and outputted per task completed.

1000% warranted. not sure what level of peak echo bubble you live in where this level of critiscism feels like you need to defend a ONE TRILLION DOLLAH company.

seriously... priorities yeah?

Re: Maximizing the value of your Claude Code sessions

#110

Post by NamlchakKhandro »

crthpl wrote: post #102
mccoyb wrote: post #7

Earlier quoted context omitted.

It's very easy to understand: - I'm happy to learn how to use tools efficiently - I like to be able to inspect my tools - I'm against tools changing underneath me Are you against any of these points?

what specifically has changed about Claude Code?

https://cchistory.mariozechner.at

and as is normal for hosted models, almost everything... based on load flucation they may even send your prompt to a quantised model

Post reply on HN