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

61–70 of 206 posts

Re: Maximizing the value of your Claude Code sessions

#61

Post by runeblaze »

mccoyb wrote: post #18
runeblaze wrote: post #13

Earlier quoted context omitted.

dude, if you try to do harness development yourself you will realize that most things said in this blogpost is shared with any ${sufficiently_advanced_harness}. this is not really claude-specific, this is just how this class of tools, OSS or not, works

That's not my complaint. I know well the concerns of agent harnesses. My complaint is that this is a low-dimensional projection of a system which I have no insight into, and therefore, I cannot evaluate the tips myself against their source. Am I to believe the creators, knowing full well that the source will, as Boris Cherny put it in a recent interview, be deleted and rewritten from scratch at the release of the nex…

> which I have no insight into

i guess you do? claude code is the commercial closed sourced version provides by ant. reading a mini version of vllm or sglang and then read codex source code or grok build source code will teach you all things taught by this article, fully in the open

it is like saying that you have no insights into some $commercial_db_system which is kinda true but imagine if the article is to teach you indices, query normalization, etc..

Re: Maximizing the value of your Claude Code sessions

#62

Post by apercu »

DangitBobby wrote: post #55
apercu wrote: post #37

I didn't read the whole thing, but I got my back up at the headline and my first reaction is now even the "AI" companies are telling you that "you're holding it wrong". I mean, they told us "just talk naturally to the AI because it's so much smarter than all you meatbags" and now it's “for best results, please learn to manage context windows, prompt caching, cache invalidation, model switching, output verbosity and w…

There is no shortage of literature on how to communicate effectively with real people.

I'm doing my best to interpret your comment but if I parse it it seems like you think my complaint is "I shouldn't have to express myself clearly" when really its "Why am I being asked to understand and manually manage the implementation details of the product in order to keep it working efficiently?".

Unless I am fully not understanding your comment and you don't actually mean “humans require communication skills too” which in honesty feels orthogonal to my complaint.

Re: Maximizing the value of your Claude Code sessions

#63

Post by apt-apt-apt-apt »

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?

I don't use sub-agents, only the normal linear message-response flow.

Re: Maximizing the value of your Claude Code sessions

#64

Post by Doohickey-d »

kristjansson wrote: post #42
guessmyname wrote: post #38

Earlier quoted context omitted.

> 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…

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

Yes, now the poster of the issue just needs to (tell claude to) write a bot which posts a "bump" comment every 17 days, and the bots will cancel each other out.

Re: Maximizing the value of your Claude Code sessions

#65

Post by g4cg54g54 »

ahurmazda wrote: post #33

What’s the point of running /clear vs starting a brand new session. At least with the latter I have session history, no? Pardon my ignorance since Claude isn’t my primary driver

Its all lies anyhow:

- https://github.com/anthropics/claude-code/issues/47756 > [BUG] /clear bleeds into the next session (what also breaks cache)

- https://github.com/anthropics/claude-code/issues/47098 > [BUG] new sessions will *never* hit a (full)cache

Re: Maximizing the value of your Claude Code sessions

#67

Post by Banditoz »

dist-epoch wrote: post #45
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'm curious if you also laugh at articles about how to reduce your AWS bill, or how to add indices to Postgres such that you can run it on cheaper hardware.

I think you're conflating two different things here. I am not aware of any DB optimization articles that say "trust me bro, throw your data, don't build indices, it'll Just Work™!"

Re: Maximizing the value of your Claude Code sessions

#68

Post by ed_mercer »

guessmyname wrote: post #41
bytestrix wrote: post #21

do people use the Caveman, RTK plugins

No, because it is useless. • https://news.ycombinator.com/item?id=49080605 (JetBrains, Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test) • https://news.ycombinator.com/item?id=48588755 (The Token Compression Illusion: Why I'm Skeptical of RTK )

If it can save 10% of tokens, how is that useless?

Re: Maximizing the value of your Claude Code sessions

#69

Post by superasn »

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 limits.

- Plus your handoff files becomes a useful piece of project memory that you can reference later.

I find this much more useful than /compact or /clear because the context is saved in something portable instead of being tied to one session and i've seen better results doing this every 20 messages or so than running long sessions.

Re: Maximizing the value of your Claude Code sessions

#70

Post by DangitBobby »

apercu wrote: post #62
DangitBobby wrote: post #55

Earlier quoted context omitted.

There is no shortage of literature on how to communicate effectively with real people.

I'm doing my best to interpret your comment but if I parse it it seems like you think my complaint is "I shouldn't have to express myself clearly" when really its "Why am I being asked to understand and manually manage the implementation details of the product in order to keep it working efficiently?". Unless I am fully not understanding your comment and you don't actually mean “humans require communication skills to…

> I mean, they told us "just talk naturally to the AI because it's so much smarter than all you meatbags" and now it's “for best results, please learn to manage context windows, prompt caching, cache invalidation, model switching, output verbosity and when to manually clear or compact your session.”

It's true both that it can be smarter than all us meat bags and that talking to it a certain way gets better results. On some of the things it's a limitation of the technology and on some of the others it's just how information and effort work in any context. I don't see it as orthogonal to your complaint, I see your complaint as misplaced frustration, like Anthropic invented GIGO and compute so they'd have an excuse to write a blog post.

Post reply on HN