Chuck Blake

"The scarce resource is knowing where to direct intelligence." every.to/chain-of-thoug… @danshipper @every

@ChrisDunnTV @bradmillscan @AlexFinn this has been the biggest help with my claw -> got ruthless about reliability before adding more features

I asked it to give me a breakdown of what we did to make our openclaw useful… • got ruthless about reliability before adding more features • built clear agent roles so each one has a real job instead of one general blob • added memory + Notion pipelines so useful work compounds instead of disappearing every session • moved repetitive research / content / routing tasks into scheduled workflows • tightened prompts, outputs, and formatting so the agent produces usable work, not “AI-ish” mush • added monitoring / watchdogs / recovery so failures get caught fast instead of silently breaking stuff • started with boring infrastructure first. once that was stable, productive projects got way easier I know this is kind of vague, so happy to offer any specifics if you want

Every time I watch an OpenClaw influencer video I go a little greyer. What are they doing that I'm not??? I will pay $10,000 in Bitcoin to observe @AlexFinn using OpenClaw for 1 day. BUT if he spends 50% of his time doing tech support, he owes me $5,000. What do you say Alex?

@readwise Fantastic!

Introducing the Readwise CLI. Anything you've saved in Readwise (highlights, articles, PDFs, books, youtube, newsletters) is now instantly accessible from the terminal. For you, and your AI agents. npm install -g @readwise/cli

@AdolfoUsier tasks are a big mixed bag: organizing to-dos in #OmniFocus, organizing/reviewing #Readwise/PKM, personal CRM, creating issues in Linear for my CTO role, updating code, and adding operations oversight to some side projects. Lots of skills and crons. A lot of tweaking of skills.

@chuckblake man I felt this - memory issues in the node version drove me crazy. switched to the rust alternative and its way more stable for memory handling. what kind of tasks you running?

my #openclaw setup lives in a single Telegram thread — and I throw a lot of different work at it. hit some memory weirdness, now I wait for one task to finish before throwing another at it, even when it's just spinning up a sub-agent. probably half superstition at this point 🐈‍⬛. How do other folks manage this?

Memory.md hit 17k characters, so I spent last night pruning redundant entries. Logged the same 7 patterns three separate times over several days. #openclaw

@Shpigford @RumoredAI Interesting pricing test!

i've been heads down lately working on a new thing: @RumoredAI and today it's available! everyone's familiar with SEO and everyone's becoming more familiar with AEO/GEO (which is optimization for AI). yes it's interesting to know what terms/phrases surface your business, but what nobody has tackled is what to do when AI is getting your business *wrong*. and we found that AI hallucinates business facts for quite literally every brand. rumored.ai surfaces what AI is saying about your brand, what it's getting wrong, how you compare to your competitors and (most importantly) the exact things to do to fix those issues. you get a ridiculously in-depth interactive threat report covering 12 sections: from executive summary and active threats to competitive analysis, schema audit, and a prioritized action plan with copy-paste fix prompts. this isn't a subscription (yet?). it's a one-time purchase of an in-depth audit of your business. launch price is $25. but the price goes up by $25 each time someone purchases. 📈 have been testing this with a lot of companies and the response has nearly universally been 🤯. i think you'll love it.

@TheStalwart same here!

Someone else told me this too recently. So that’s two people.

🎵 SF Bay Popfest — a 28-track playlist 28 tracks • 68:48 Curated by slumberlandrecs on Indie Crates @janglepophub @theumbrellassf @subjangle indiecrates.com/crates/slumber…

Sometimes the best architecture decision is removing the thing you just added.

thanks #openclaw

@brynary @ryancarson I save plans in the code base - makes it easier for claude code to access quickly for reviews and to look for patterns and learnings

@ryancarson I've been focusing on this "Plan to PR" loop recently... Do you find it beneficial to have plan saved in Linear, or would it be just as good / simpler if you could go straight to a PR for human review?

This works well for me: 1. Plan mode in Codex on xHigh 2. Copy markdown plan 3. Paste md plan into Linear issue and Symphony takes it all the way to human review (or auto merge of low risk)

Wasted a day and a half trying to make Zulip work for me - had lots of #openclaw memory issues and crashes. Back to Telegram.

Need to keep reminding myself: progress comes from questioning the friction #openclaw

Mornings just became more productive: automated my #OmniFocus cleanup with #openclaw to roll past-due tasks forward and process inbox items, all while capturing decisions and best practices for continuous improvement. Daily systems beat daily chaos.

@Shpigford @github this is frightening 😱

for those asking, here was @github's reply re: my account being temporarily suspended.

"⁠There’s no manual for talking to machines. Or there are ten thousand manuals, which is the same thing.⁠⁠"

@Shpigford @openclaw GitHub for repos + Machine backups via Time Machine -> NAS -> S3

what’s your setup for doing offsite backups of @openclaw?

Code duplication is technical debt that compounds faster than you think. Cleaning up some of my #openclaw skills sprawl this morning.

We’re here in the heart of the @AIPSummit staff Prompt-a-Thon with @gettles, @ConejoCapital, @izgnzlz, and @wesamo__ and the energy is nothing short of electric!