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

Claude Code Routines

code.claude.com

Post reply on HN
Print view View original

321–330 of 451 posts

Re: Claude Code Routines

#321

Post by winrid »

bluegatty wrote: post #157
comboy wrote: post #107

Unrelated, but Claude was performing so tragically last few days, maybe week(s), but days mostly, that I had to reluctantly switch. Reluctantly because I enjoy it. Even the most basic stuff, like most python scripts it has to rerun because of some syntax error. The new reality of coding took away one of the best things for me - that the computer always just does what it is told to do. If the results are wrong it mean…

Codex with 5.4 xhigh. It's a bad communicator but does the job.

It's bad at long running tasks.

Re: Claude Code Routines

#322

Post by ulrikrasmussen »

joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

I agree with your analysis. Platforms are some of the most profitable business models because they come with vendor lock-in, but they are always shittier on the long run compared to commodities. Platforms are a way for companies to capture part of the market and decrease competition by increasing the cost of changing vendors.

Re: Claude Code Routines

#324

Post by dgb23 »

giancarlostoro wrote: post #86
minimaxir wrote: post #2

Given the alleged recent extreme reduction in Claude Code usage limits ( https://news.ycombinator.com/item?id=47739260 ), how do these more autonomous tools work within that constraint? Are they effectively only usable with a 20x Max plan? EDIT: This comment is apparently [dead] and idk why.

I've been talking to friends about this extensively, and read all sorts of different social media posts on X where people deep dove things (I'm at work so I don't have any links handy - though I did submit one on HN, grain of salt, unsure how valid it is but it was interesting: https://news.ycombinator.com/item?id=47752049 ). I think the real issue stems from the 1 Million token context window change. They did not an…

The future of harnesses cannot be „resend the whole history on every step“ or whatever this terrible compaction is.

Most of the context is unstructured fluff, much of it is distracting or even plain wrong. Especially the „thinking“ tokens are often completely disjoint halucinations that don’t make any sense.

I think what will have to happen is that context looks less like a long chat and action log and more like a structured, short, schema validated state description, plus a short log trace that only grows until a checkpoint is reached, which produces a new state.

Re: Claude Code Routines

#325

Post by bluegatty »

winrid wrote: post #321
bluegatty wrote: post #157

Earlier quoted context omitted.

Codex with 5.4 xhigh. It's a bad communicator but does the job.

It's bad at long running tasks.

Yes and no. It's bad because of shorter context but it does have auto-compaction which was much better than Claude. If you provide it documentation to work from and re-reference, it works long-running.

Honestly - 'every inch of IQ delta' seems to be worth it over anything else.

I'm a long time Claude Code supporter - and I'm ashamed to admit how instantly I dropped it when discovering how much better 5.4 is.

I don't trust Claude anymore for anything that requires heavy thinking - Codex always finds flaws in the logic.

But this happens every few months.

Re: Claude Code Routines

#326

Post by wazHFsRy »

eranation wrote: post #54

I've been using it for a while (it was just called "Scheduled", so I assume this is an attempt to rebrand it?) It was a bit buggy, but it seems to work better now. Some use cases that worked for me: 1. Go over a slack channel used for feedback for an internal tool, triage, open issues, fix obvious ones, reply with the PR link. Some devs liked it, some freaked out. I kept it. 2. Surprisingly non code related - give me…

Same here it just feels like something so simple, I’d rather have it under my own control. That way I can keep it independent of claude as well. I use it for all kind of routine tasks like updating the summary of projects I am working on or tracking some personal activities. My setup looks like this: https://www.dev-log.me/click_recurring_tasks_for_claude/

Re: Claude Code Routines

#327

Post by simonjgreen »

joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

Completely agree. Use of features like this places one the wrong side of the vendors moat, increasing switching cost, decreasing competitive pressure.

Re: Claude Code Routines

#328

Post by superjan »

hdjrudni wrote: post #318
joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

I also don't see the value add here... "schedule" is just a cron. "GitHub Event" is probably a 20-minute integration, which Claude itself can write for you. Maybe there's something I'm not seeing here, but I never want to outsource something so simple to a live service.

For Anthropic, it is valuable that they control the scheduling, so they can move jobs around to use the infa when it is relatively quiet. If you let customers choose the time, a lot of work will start at whole hours.

Re: Claude Code Routines

#329

Post by JyB »

taytus wrote: post #94
joshstrange wrote: post #60

Earlier quoted context omitted.

The restrictions are dumb not because they're lower than any of us want them to be, but because they're unclear. Every time Claude comes up on Hacker News, someone asks this question. And every time people chime in to agree that they also are unclear or someone weighs in saying, no, it's totally clear, while proceeding not to point at any official resource and/or to "explain" the rules in a that is incompatible with…

You are arguing something different. My point is that they must apply these restrictions. Do I think they could have calculated their growth a little better? Yes, of course, but hindsight is 20/20.

Restrictions don’t have to be confusing, they can be clear. You are missing the whole point.
Post reply on HN