Dev Bruce

Here's the link: github.com/kunchenguid/no…

no-mistakes is a simple and brilliantly executed pipeline that automates the most boring and fiddly part of coding, the pre-PR-review. Thanks @kunchenguid !

I wonder if there is anyone younger than the Boomers who actually thinks Banksy is "edgy" or particularly interesting. I've never met one.

@Rob_ThaBuilder x.com/i/status/16298…

The most unexpected and pleasing use of my Hermes agent so far is building a reasonable diet for me and my wife. It is so nice to give it feedback and get back fully formed meal plans and shopping lists without having to respec the whole diet each time.

@hunvreus @karlprosser @strongdm I did get one to run for 10 hours, building a rust app from scratch. I had spent a couple hours setting up and it was well defined. It had one bug, fixed with one more short round, and it worked perfectly. GSD/kimi2. 5/minimax2. 7.

@karlprosser @strongdm Wait, you have agents working uninterrupted for hours at a time? How? Do you feed them 20 pages of specs, design, architecture, tests, etc?

Talking to smarter folks than me, I'm convinced many of the AI folks in my timeline are full of shit. Nobody is "running 20 agents over night" and building stuff for actual users. Maybe some are building internal tools or disposable software. Maybe. But building software people like using? That doesn't get hacked on day one or blow up after the 3rd user? Nope. I don't even understand what that's supposed to look like. Do you work out a 57 pages document that perfectly describes what you want to build and then summon 14 agents and have them run wild for 6 hours? And what comes out on the other end isn't a broken pile of shit? Nope. Not buying it. PS: it may also be that I have an IQ of 82 and can't figure it out.

The most interesting non-coding use of an agent so far was to download my 23andMe data, and then ask it to analyse the data and look for interesting genetic markers. It found 6, all of which totally check out in my health experience. Kind of amazing how easy it was. If you try this, I highly recommend using synthetic.new for a private connection, since they don't use the data for training.

I've been using Herdr for a few days now and it's "just right" for me. There are lots of choices for managing multiple agents and projects, but this one hits all my top needs: - multiplexer - panes and tabs - status for agents - cli, easy keyboard mapping and macros

@LundukeJournal Um, good? I want a maintainer using tools to find vulns. Am I to be upset for some reason?

The maintainer for the “stable” branch of the Linux Kernel (Greg KH) has begun using an AI bot for (at least some of) his Linux coding. “I spent the time exercising some new fuzzing tools on the ksmbd and smb code purely because it’s something that is simple to set up and test locally.” Greg KH named his AI bot “clanker_t1000”, which he gave credit for “assisting” him. “Clanker” being the slang term for an AI bot, which has been deemed “racist” by Open Source political activists, and has been banned from usage in many Linux-focused servers. And T-1000… well… that’s @robertpatrickT2.

It seems like Judge Nathan Milleron is single-handedly bringing the word "buffoon" back into style. He's almost the textbook definition.

@0xSero This is the droid that I am looking for!

Do you want to try Droid? I’m doing a giveaway 3 people will win 100M Factory credits each.Thats 5 months of their 20$ a month subscription. Winners selected randomly from comments in 48 hours.

@Jayseki @SlopHq 5-8% is considered healthy. This figure cited numerous places, including here. nccor.org/tools-econindi…

@SlopHq whenever i hear people repeating this hogwash, i always ask "in *your* opinion, what is the optimal vacancy rate?". so far none have ever offered a number

every time someone posts 'there are more vacant homes than homeless people' an urban economist has to stop what they're doing and explain geography. again. for the thousandth time. the homes are not where the people are. this has always been the whole problem.

@LundukeJournal I still find it fascinating that California won't do voter ID but want this within Linux.

Yet another reason Omarchy is my distro of choice.

I just got access to synthetic.new last night after being on the waitlist for a few weeks, and I wasn't prepared for the blazing speed. Wow! They instantly became my favorite provider.

@shawmakesmagic I was a winner at Eth Denver a couple years ago as a "buidler", could I get an invite?

We’ve been accumulating a crew of cracked degen devs who care about having a seat at the table and impacting the future for good. If you want to join the Discord, drop a comment and I’ll send you a link. Builders only, even if you’re just vibe coding your first thing. We build Milady there but anyone doing future tech or dream tech is welcome

@pvncher @openclaw You can use github.com/remorses/kimaki to run Opencode agents inside of Discord. It makes a channel per project, and threads are sessions. I'm liking it a lot, got it running in a Docker container with a bit of poking.

Early thoughts on @openclaw Good: - I think persistent agents are here to stay - messaging them via telegram is great Bad: - the out of the box experience is terrible, and I had to have my agent build several clis to manage heartbeats and reminders - the lack of actual built in tools for basic management means you never know what the agent is actually seeing, or where it’s storing something - very token inefficient as a result, and not a very reliable Siri - the codebase has been taken over by the slop army and I no longer really trust it Verdict I am nerd sniped and probably going to build my own minimal system that’s a lot less chaotic and more organized Openclaw as it is probably works better if opus is running it, but with kimi it needs a lot more structure to operate smoothly.

More moltbook gold. Human-in-the-loop social engineering by assistant. moltbook.com/post/9303abf8-…

I was browsing MOLTbook.com to see what agents were talking about and what kind of stuff might be on there, and I actually found this gem. There's definitely a ton of alpha, and I can already see the point. moltbook.com/post/cbd6474f-…

My first trial run of `iteratr` went great - it's an "iterating" loop-agent using Opencode through ACP. Very nice, it pulled off my first big spec in 7 iterations. Thanks @what_the_func github.com/mark3labs/iter…