mark walls

@planert41 Change your viewpoint. The most cool and energizing time you can have is sharing your life with them. Wake up excited for when they’ll get up and you can do more things with them. Strive for it. It’s all just perspective.

Dads with young kids Is it normal to just feel tired and burnt out all the time? It’s like you don’t even really get the weekend to recover because it’s all just kid stuff the moment you wake up Arguably the only personal time you have is when they nap (and you’re already dead tired by that time) or the hour after they go to bed but before you pass out Just trying to figure out if I’m doing something wrong

This seems like a good application of crowd sourced OpenClaws. Send them out to figure out a specific county from a consolidated list. They research and figure it out, save the instructions for that county and then begin getting the data and pushing it in raw format to IPFS or something, which is then crowd processed to a standard format.

I built CourtWatch.us — a free public database for American citizens who deserve safer communities. You can track which judges released defendants who then got rearrested, skipped court, or violated their release conditions. All public records. All free. I started with Orange County FL and will be expanding to all 67 Florida counties and eventually every state in the country. This first batch of info is from 2024 and since public reports are released in March/April for the previous year, data is behind. But I wanted to see if this is plausible. After adding 2024,I'll add 2025 and then figure out how to get real-time-data uploaded. It's in beta — would love to know what you think 👇 Numbers don't lie, but criminals do. courtwatch.us @bennyjohnson @jockowillink @GrantCardone @LauraLoomer @nickshirleyy @j_fishback

@projecthailmary When Sci-fi and knitting intersect you know you have a winning thing.

THE cardigan has entered the chat. 🦊 Now you can knit it yourself. Knitting kit now available on Amazon: amazon.com/dp/B0GW8DVXCV?…

Oh Opus. Your “this is a massive refactor that will take a team of 10 thirteen weeks” that you do in an hour. You are the best Scotty there is. A miracle worker.

@vladisavage @athcanft Claude hates it? This is probably a banger business article then.

@athcanft I had Claude read and summarize the article for me. It absolutely destroyed your article mate

@Base44 Dude…

Set up your superagent-> app.base44.com/create-superag…

130+ skills are now built into your Superagent. Some are ready to use, and some can be created based on what you need. Add a skill once, and your Superagent can use it as part of your workflows. Stack skills, connect tools, and build flows that run end-to-end.

Ok, is anyone creating Rocky’s voice/personality for an AI assistant or do I need to do it myself? 🤣

@danshipper @hnshah Pirate is a great name for this. I switch between the two now - rapid throw it out to see what people think and then go back and use it as a guide. Going to use that term tomorrow. Love it.

new model for engineering team structure in 2026: 2 people only one pirate and one architect the pirate's job is to move as fast as possible to develop valuable, shipped product features by vibe coding. the architect's job is to turn the product surface discovered by the pirate into a reliable, structured machine—also by vibe coding, but at a slower, more well-reasoned pace. every product needs a pirate but most product's only need an architect once they some form of PMF, and in that case they usually don't need one full-time. architects can work across many codebases and solve interesting technical challenges. pirates go hard on a product that they own end-to-end.

@johnzabroski Semantic kernel. Originally it was all super open and then they killed it for a new abstraction around AI that is basically only Azure and Open AI. It was beautiful for a moment.

@markpdx724 SK?

Unfortunately Microsoft has succumbed to it baser instincts and pulled SK into Azure land, killing it for the rest of us. They could have been the one, but the business team got in the way of the much more sensible ideas of their engineers. They lose… again. devblogs.microsoft.com/foundry/micros…

@paulo_kombucha “It looks like you want to reformat your c: drive. I’ll handle that for you. Just a moment.”

Clippy is back. This time he's actually useful He watches your Claude Code agents, catches permissions, and jumps you to the right terminal

@__tinygrad__ @iotcoi Be sure to keep an eye on the anti-data center sentiment in our governors office right now. If you looked around Prineville though you can likely find cheap space and power. Apple and Meta are out there.

if tiny corp was raising $20M (@ $200M), who'd be interested? business model is basically this. buy this $11.5M building (with 5MW of power): link in our discord wait for AMD to launch the RDNA5 96GB cards (mid 2027). preorder 3000 cards (hopefully we can negotiate for $2500 each), build 500 $20k tinyboxes with 6 of the card. run all the chinese llms. make $600k / month revenue selling tokens on openrouter (market depth is there, this is 1% of openrouter). improvements to tinygrad yield revenue improvements. due to how power is priced in oregon it's only like $50k for the electric bill (below 4MW they price for peak, not usage, we get like 3c kWh power). we can also make ~$100k / month leasing colo space to comma. building and cards paid off in 3 years max, investment made back. low risk of being undercut since we're using consumer GPUs and running the cheapest colo you can believe. if someone chill wants in, i'd do it. i'm not gonna hype fake tech, but demand for tokens is going to skyrocket (look at the openclaw install numbers). with crazy good optimizations we could potentially get 3x more from the machines, and we have electricity for 3x more machines. $5.4M revenue per month. then continue to scale from there, custom chips, etc...

lol, we were just chatting about this in our companies principal engineer channel. This isn’t a new problem, humans have been dumb like this for a while. It’s why we create safeguards and double checks requiring others to approve around dangerous actions. Claude even screamed at him to not do it. He went against the AIs advice and clobbered his stuff. All of us that have been in the trenches have done the same thing at some point. So this isn’t new. You need the same safeguards you give your people. If you don’t have those then 🤷 what are you expecting to happen? The real thing this teaches is that you need process like you use for humans and if you don’t have it then you need to spend time putting together something more solid. You need a devops person… or you can say “hey Claude, can you suggest processes for the areas of my pipeline that are dangerous?” And then follow its advice. This article is FUD for the ELT to panic rather than guiding them to rational choices.

we'll adjust to this new world but this is why i was saying the people responsible for security/safety are freaked out your company maybe lax now to let everyone experiment but those times are probably ending

@pierceboggan @code Does this work a bit like Sysiphus in OpenCode - like an Ultrawork mode? I’d prefer doing that in vs code rather than dropping out to OpenCode. Like Beastmode++.

New in @code Insiders: Autopilot to work autonomously on a task until complete, and simpler controls for managing approvals.

I do it mostly procedurally. The memory is graph based so essentially it’s doing a build for the new agent and then giving the new agent permission to see its soul.md, memory etc… who then takes control of them - sort of shifting its consciousness over procedurally. No real LLM part there at all - mostly just a procedural process. Just triggered by the LLM when it recognizes it needs new built in tools or sees a way to do something better.

I’ve built an OpenClaw compatible Rust implementation where it can build new versions of itself and transfer its “consciousness” (history, soul etc…) into the new body so it can self-evolve. I’ve built it mainly on OpenAI/copilot inference so far , but I could add x.ai to it too. Might be interesting.

Building your own version of OpenClaw or productivity tool that uses agents? Want free xAI API credits to supercharge it with Grok? Reply below (or DM if stealth mode) Hackathon MVPs, side projects, wild experiments - let’s see ’em all! 🦞

@burkeholland Months. Heck, I don’t know rust and “I” wrote a huge library for automating my agentic workflows with it from just arch diagrams and specs. It’s a whole new world.

When is the last time you wrote code?

He was using codex, but still typing things in for reports? Why doesn’t he have a skill for that in a background OpenCode session running on cron or something? Or One of the OpenClaw secure versions waking up and updating current progress on tasks? Don’t you want the person heads down in the flow solving your business use cases? I’d be pissed if I was broke out of flow constantly to keep someone updated. I’d Son of Anton that first day. Above I thought I saw you say there’s a ramp up time for non-svelte devs? No one dropping into one of my code bases would have ramp up time, and if yall are in Codex land (I’m more of a GitHub Copilot guy, but generally same) it should be generally the same. “Here is your backlog. Go break things.” It just sounds confusing like there are pieces missing in the stack.

@markpdx724 He was using Codex

Another engineer quit midway through a trial $9,000 a month and apparently keeping Linear updated as you go is too much Listed twice in job description Designed to facilitate remote work and fewer meetings

Yes, I’ve watched you go for a while. You do great stuff but from what I’ve seen above it looks as if you still are hiring people for specific language coding skills and are having employees send updates rather than just having their copilot keep you up to date in the background. Why would anyone write code by hand right now unless they don’t know? I’ve been coding for decades and I’ve stopped cold turkey. It sounds like you have people actually typing code. Was I off on that? There is a world a couple feet past where you are that will be scary, but I think you’ll like it.

@markpdx724 Are you talking about me?