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

151–160 of 206 posts

Re: Maximizing the value of your Claude Code sessions

#151

Post by AlfeG »

alekstret wrote: post #142

Here is my working flow, confirmed by more than 400 pr merged over the last 4 months. More than half of them were following my current strategy: 1. My agent writes code. 2. Then it creates tests and verifies that all of them actually work, not just pass. To do this, my agent writes the test, then it deletes the code it covers, reruns the test, confirms it goes red, and finally puts the code back. 3. I receive the rea…

I tend to do code review in separate session. So that context is not affecting judgments.

Re: Maximizing the value of your Claude Code sessions

#152

Post by fireflash38 »

guessmyname wrote: post #38
rhaksw wrote: post #25

> @-mention files instead of naming them Love Claude, but the @ mention is broken in the desktop app. For the same project if I type the same query "@ephem" I get: CLI: https://imgur.com/a/VZMUCOa (good, relevant results) Desktop: https://imgur.com/a/QLSo4Ms (bad, irrelevant) Opened issue for this and it was automatically closed: https://github.com/anthropics/claude-code/issues/71421 I could have written the issue be…

> Opened issue for this and it was automatically closed: […] Clarification: It wasn’t closed on submission though. It sat open ~17 days, a bot marked it stale, and it closed when nobody responded to the stale label. The two-phase thing is the part I didn’t know until recently: the stale label is basically asking “is this still relevant?”, and answering it makes the bot back off next time around. nixpkgs does the same…

Stale closing bugs is the worst.

Just because someone moved on from your broke ass product doesn't mean the bug was fixed. I can't count how many times I'll find an old bug still there years later closed with 5+ duplicate issues all linked back to the same closed github issue that was closed as stale.

It's just bullshit. Having a lower count on your issue tracker doesn't make the actual bugs disappear folks

Re: Maximizing the value of your Claude Code sessions

#153

Post by 9dev »

user43928 wrote: post #122
9dev wrote: post #39

Earlier quoted context omitted.

You can do tons more, really. There’s even a built-in /statusline command to modify it; mine shows both context window usage alongside session and weekly limit, all of them as progress bars. Just ask Claude to do it.

That's what is shown by default in the app. I'll never understand why anyone would want to restrict themselves to a terminal interface instead, and I say this as a Vim user.

> That's what is shown by default in the app.

It is shown in Claude Desktop if you care to check in Settings > Usage, sure - but not in Claude Code, updated as you work with it.

> I'll never understand why anyone would want to restrict themselves to a terminal interface instead, and I say this as a Vim user.

I usually work with Claude in tandem, that is: The agent is actively working while I am either reviewing code or making changes myself in other places. So this means I want to work within my IDE. If you use Claude Code to vibe-code without interacting with the codebase at all, the Desktop app is probably fine, but for all other purposes, you'll need to run it either in the CLI or integrated into your editor.

And since I use different editors and don't like using either a sub-par U integration or locking myself into the harness of my IDE's vendor, I prefer the CLI as a universal way of running Claude Code.

Re: Maximizing the value of your Claude Code sessions

#154

Post by DangitBobby »

NamlchakKhandro wrote: post #109
DangitBobby wrote: post #51

Earlier quoted context omitted.

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?

I don't typically decide things on the basis of whether it's a trillion dollar company. If it were a blog post about puppy slaughter I wouldn't be defending it.

Re: Maximizing the value of your Claude Code sessions

#155

Post by dboreham »

xpct wrote: post #146
superasn wrote: post #69

Recently I came across the /handoff skill, which I've been using a lot. I find it much better than /compact. Basically: - /handoff file creates a short document with the important context from your current session and maybe next steps as checklist. - You can then start a fresh session with /continue file - You can also hand the work from Claude to ChatGPT, or the other way around. Very useful at time of session limit…

Ah I've been doing handoff manually by asking the model to do it. If Claude's handoff includes better context than its summaries, it's probably worth checking out.

I prefer to avoid its internal magic mechanisms. The LLM can read documents like a human (actually better since...no ADD) so I ask it to create documents. This also has the benefit that you can change to a different AI tool and the information is still usable.

Re: Maximizing the value of your Claude Code sessions

#156

Post by ultrasandwich »

alekstret wrote: post #142

Here is my working flow, confirmed by more than 400 pr merged over the last 4 months. More than half of them were following my current strategy: 1. My agent writes code. 2. Then it creates tests and verifies that all of them actually work, not just pass. To do this, my agent writes the test, then it deletes the code it covers, reruns the test, confirms it goes red, and finally puts the code back. 3. I receive the rea…

> To do this, my agent writes the test, then it deletes the code it covers, reruns the test, confirms it goes red, and finally puts the code back.

Why? Are you aware of red/green/refactor?

Re: Maximizing the value of your Claude Code sessions

#157

Post by namjh »

lovasoa wrote: post #124

I don't understand why changing effort levels busts the cache. Couldn't effort levels be a decoding-only thing where they just change the probability of the token? Are they literally adding a hidden system prompt that says "effort level: $level" ?

In that way the autoregressive nature of LLM won't let itself "plan" to reason with the intended budget. It doesn't "look ahead".

Re: Maximizing the value of your Claude Code sessions

#158

Post by Phemist »

apt-apt-apt-apt wrote: post #98
Esras wrote: post #79

Earlier quoted context omitted.

You may be running into a "known" bug with Claude Code: https://github.com/anthropics/claude-code/issues/63930

This happens all the time and drives me bananas. It seems to be regular file edits rather than parallel tool calls. I'm sitting on 1.6m cache write even now with 468k in /context. It drives my session costs above $100 regularly. Can someone from Anthropic look into this?

Incentives to optimize cache-usage are only aligned between anthropic and you, dear user, when there is not enough compute available to serve the tokens fresh. Apparently enough compute is now available that frugal usage is no longer a requirement and user cost/profit maximization is now the name of the game. I would expect to see more and more "cache-busting" strategies implemented in order to both eek out marginal performance increases and to heavily increase profit.

Re: Maximizing the value of your Claude Code sessions

#159

Post by skybrian »

superasn wrote: post #69

Recently I came across the /handoff skill, which I've been using a lot. I find it much better than /compact. Basically: - /handoff file creates a short document with the important context from your current session and maybe next steps as checklist. - You can then start a fresh session with /continue file - You can also hand the work from Claude to ChatGPT, or the other way around. Very useful at time of session limit…

I do something similar but without using a skill.

It might be even better if the harness were to automatically write a handoff note under some circumstances? If the user is away and the cache is going to expire, that would be a good time to do it.

Re: Maximizing the value of your Claude Code sessions

#160

Post by apercu »

DangitBobby wrote: post #91
apercu wrote: post #73

Earlier quoted context omitted.

Huh. And to me it’s like “I can’t believe Anthropic has the audacity to post that and I can’t believe my peers defend it” Oh well.

And I in turn can't believe your response to the post. Different strokes for different folks. I understand that HN fucking hates everything and everyone, especially big model providers at the moment, but this shit doesn't make any sense to me and you people are starting to actually make me crazy.

"Dang it, Bobby" :)
Post reply on HN