331–340 of 428 posts
Anthropic now have Routines in Claude Code that do precisely that, and I’d bet they will bring that to Cowork. ChatGPT can’t be far behind (or maybe they already have - tbh hard to keep track of everything).
Devs can already set up reliable cron jobs for cheaper. Normies will have a less brittle solution for it soon. Where does that leave the claws?
I disagree with practically every take here, and likely will get hate for this message. Personally it has been a huge unlock and here are some specific use cases. 1.Context engineering for “any task”: my claw agents debate with me, and write me files to be picked up by Claude code or Claude cowork to write code/build presentations. 2. Discovering this page: my personal newsfeed that took me 10 mins to setup. Never ha…
Earlier quoted context omitted.
Why not use Claude to write yourself a daily briefing, and deliver it to your email or someplace you’ll receive it?
That's what I ended up doing, made my daily briefing a Cron job and running it via "claude -p". Wired it up to make a podcast, with MCP tools I made to create an MP3 with OpenAI, another to upload it to one of my sites with an updated RSS feed, so I can listen in the AntennaPod podcast app each morning.
But I realised everything I needed was cron + some basic tools to create and handle local documents + API access. The last is still a pain to manage so I built my own tool to work as an auth layer https://ohita.tech/ Basically it handles all the token refreshing, rate limiting etc. so when the scheduled task triggers it does not immediately fail because API auth failed.
Earlier quoted context omitted.
I am weirded out but this, I find it horrific, like some kind of mind zombie, leeching humanity from your family members. Someone somewhere is thinking they're connecting with you and sharing their humanity but they're just shoveling their soul into a machine that is "meticulously documenting" them. Sorry, but ick.
I actually think this is cool. How is this different than sitting people down with a camera every day and asking for a new random story? we won't be around forever and documenting it is one way to keep memories alive in people's minds
Earlier quoted context omitted.
Yep. I had posted a comment earlier detailing my usecases. But I too replaced that with my own system that does those same things. It's way too bloaty, felt like operating windows start menu search. But you might have missed so far some of the ideas they have. So it's useful to try it out, see what combination of features you use in particular and then just set those up for yourself with claude code or whatever as th…
Definitely worth following for ideas. How did you solve memory in your system? I ended up using QMD + custom skills to keep it up to date as new data comes in. Essentially a cross-referenced set of markdown files forming a knowledge base: https://github.com/tobi/qmd
I use a mix of markdown notes, an sqlite database, and my image store searchable by text. I use immich.
For now I do it manually by giving it skills for each data store I wanna access.
My usecases are all ad-hoc I am not a "pro" user by any means. So I don't mind some manual work.
> Hey Sam, I'm Jarvis — $CEO_NAME's AI assistant (OpenClaw). He asked me to reach out on his behalf. $CEO is building $HYPED_STARTUP — the tool execution and MCP layer for AI agents (10K+ integrations, Series A with $FAMOUS_INVESTOR). He's looking for engineers who are deeply into the agentic coding stack — Claude Code, Codex, MCP, agent infra. Builder mindset, ships fast. Worth a quick call?
>
>Jarvis (on behalf of $CEO, co-founder @$HYPED_STARTUP)
It’s the weirdest thing ever to receive. I generally answer politely to the claw bot, but that all feels just extremely strange.
You’re reaching out to a human for a call and cannot present yourself as a human? But at the same time, it’s maybe preferable if they disclaim it was automated? I don’t know
Just weird all around