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

371–380 of 451 posts

Re: Claude Code Routines

#371

Post by munksbeer »

Nevermark wrote: post #266
ElFitz wrote: post #220

Earlier quoted context omitted.

> Not because I can't see a use-case for them, but because I have 0 trust in them > […] > Put another way, LLM companies are trying to climb the ladder to be a platform, I have zero interest in that, I was a "dumb pipe", I want a commodity, I want a provider, not a platform. That is my sentiment precisely, and a big reason why I’ve started moving away from Claude Code in the past few weeks when I realised how much of…

> Claude Code’s "Memory" feature was the tipping point for me My standing orders are the default MEMORY.md must be a stub directing Claude to another MEMORY.md file in the local folder, project, etc. All memories remain with their respective projects over syncs, moves, devices, etc. The stub must state all this clearly, and nothing else. This has worked very well. If you give the model/memory a name, that name can be…

Can you explain a bit more technically how you set this up? What is a "stub directory"?

Feel free to give a concrete example if you have time, because this sounds like something I definitely want to try out myself.

Re: Claude Code Routines

#372

Post by sumedh »

stavros wrote: post #207
dpark wrote: post #120

Earlier quoted context omitted.

They are more worried about building a moat than anything else. They want people building integrations that are difficult to undo so that they lock into the platform.

So basically what happened: 1. Anthropic realized their models weren't enough of a moat. 2. They built tools so they could expand their moat. 3. People don't want to use their tools, they want their models, and use other, better tools. 4. Anthropic bans the use of better tools, taking advantage of their model superiority to try to lock people into subpar tools. "I don't have enough of a moat so I'll use my little moa…

> I'll leave the moment another model works for me as well as Claude does.

Isnt that a large moat in itself but you are claiming its not enough?

Re: Claude Code Routines

#373

Post by stavros »

sumedh wrote: post #372
stavros wrote: post #207

Earlier quoted context omitted.

So basically what happened: 1. Anthropic realized their models weren't enough of a moat. 2. They built tools so they could expand their moat. 3. People don't want to use their tools, they want their models, and use other, better tools. 4. Anthropic bans the use of better tools, taking advantage of their model superiority to try to lock people into subpar tools. "I don't have enough of a moat so I'll use my little moa…

> I'll leave the moment another model works for me as well as Claude does. Isnt that a large moat in itself but you are claiming its not enough?

Apparently not for Anthropic, since they've been wanting to build a larger one by force. My point is you can't build a moat by forcing people, it defeats the purpose.

Re: Claude Code Routines

#374

Post by smartbit »

yohamta wrote: post #287

Claude and Open AI seems to be trying not to be 'Just a model', but this is intrinsically problematic because model can be degraded and prices only goes up once they lock-in customers. It is increasingly important for anyone who are responsible of managing 'AI workflows' to keep the sovereignty about how you use AI models. This is why I'm super excited in building the local-first workflow orchestration software calle…

> Hi HN! I'm the author of Dagu, a workflow engine that's been in development for a few years.

yohamta in https://news.ycombinator.com/item?id=44142130

Re: Claude Code Routines

#375

Post by theshrike79 »

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…

Every company is trying to become THE platform where all other tools connect to. Notion is integrating everything under the sun, as is Slack, big LLM providers have one-click MCP installation for all major services.

But... these are the "retail" tools that they sell to people organisations without the skills or knowhow to build a basic agentic loop by themselves. Complaining about these being bad and untrustworthy is like comparing a microwave dinner to something you cook yourself. Both will fill your belly equally. One requires zero skill from the user and the second one is 90% skill and 10% getting the right ingredients.

Creating a simple MVP *Claw with tool calling using a local model like gemma4 is literally a 15 minute thing. In 2-3 hours you can make it real pretty. If you base it on something like pi.dev, you can make it easily self-modifying and it can build its own safeguards.

That's all this "routines" thing is, it's just an agentic loop they launch in their cloud on a timer. Just like the scheduled tasks in Claude Cowork.

Re: Claude Code Routines

#376

Post by jeppester »

uriegas wrote: post #237
jeppester wrote: post #184

Earlier quoted context omitted.

I always hated SEO because it was not an exact science - like programming was. Too bad we've now managed to turn programming into the same annoying guesswork.

I don't really think it is turning into a guesswork. A lot of people wrote bad code before by pasting things from the internet they didn't understand. I think some people are using LLMs the same way, but it does not mean that programming has changed. But I do think that code quality is being neglected nowadays.

The guesswork lies in the "how to poke the black box in the right way", not in the code itself.

Re: Claude Code Routines

#377

Post by nojvek »

I could understand the portal before. Now it’s a gazillion things bolted on.

Enshittification is well in force.

I’d trust the huperscalers a lot more with their workers/lambda like infra to run routine jobs calling LLM APIs or deterministic code instead of Anthropic.

Anthropic is a phenomenal paid model but they have a poor reliability record.

I don’t care much if Claude code hiccups when generating code. But after the code is generated I want it to run with multiple 9s under certain latencies every single time.

Re: Claude Code Routines

#380

Post by stingraycharles »

andai wrote: post #20
whicks wrote: post #8

Earlier quoted context omitted.

I would imagine that this sort of scheduling allows them to have more predictable loads, and they may be hoping that people will schedule some of their tasks in “off hours” to reduce daytime load.

It also beats OC's heartbeat where it auto-runs every 30 minutes and runs a bunch of prompts to see if it actually needed to run or not.

It’s really, really ridiculous just how many tokens OpenClaw burns when it’s not doing anything.
Post reply on HN