LLM / local model "vibe coding"
Also! It ended up creating race conditions due to attaching listeners at the wrong point in the test (which didn't matter for this case) but I think I can modify the project's AGENTS.md to make sure it doesn't make the mistake a again.
LLM / local model "vibe coding"
I'm not sure how long it was chugging away at it, but I see in the logs that it did a few iterations and some bug fixing as it went along. The final code looks pretty much how I would have done it. I don't think this means I'll be using this feature daily, but I might give it another shot next time I have a concrete plan that I want to execute while I make dinner or whatever.
LLM / local model "vibe coding"
Last week I set my local LLM to do it's first mission where it vibe coded some integration tests for me. I added a "allow local file edits" mode to my harness a little while ago but I hadn't had time to actually give it a go. I spent some time as I was logging off work to go on a date to make a plan with the LLM to test some changes to our replication code and gave it some constraints on which shell tools it'd be auto-allowed to use and set it off.
@nilix fun! what is your theme? I don't post my body online much but it's a cartoon cat being quartered and the quarters are different aspects of my life
We should just have Techaro's Anubis be an HTTP standard that browsers implement instead of all this captcha as a service BS.
@roknrol You're right, we should never change or improve anything. Especially not something as malleable as computer software. Unless it makes everything worse of course, then we should push it through as fast as possible with zero safeguards. 🤪
Can we stop the "prove you're human" checks now that vision models can solve them better than some humans and standardize on a hashcash HTTP challenge/response so we can mitigate the scraping asymmetry while ditching the surveillance JS bloat? Please?
ADHD meds are more effective when paired with old school gabber mixes. #ProTip
@TetroniMike I think their management would need to get their head out of the AI industry's ass before they start making actual changes like this, but we can still dream :P
@TetroniMike Brave kinda went in that direction, so did some of the Web Monetization stuff a while ago. I think the crypto influence kinda poisoned the efforts though. I think it'd be cool to have something like this. More likely that Google would add something proprietary for it in their browser IMO.
local LLMs
Been revisiting local models again. The state of the art for it's size is apparently MiniCPM5 right now. It can do very basic code related tasks but it's still way too stupid to do actual tasks. Might be enough for my "speech to code to speech" idea though?
I’m hiring security engineers to join me at Factory, and you should apply!
Factory is an exceptional place to work. The team is brilliant, customers love the product, and we’re growing quickly. We’re also early enough that new hires will have real influence over what we build and how our security program develops.
Whether your strengths are in pentesting, application and product security, cloud security, corporate secu... ... https://honeypot.net/2026/09/28/im-hiring-security-engineers-to.html
Remember Aaron Swartz and the tragic fate he suffered? Remember the kids who downloaded games or MP3 files, whose parents were threatened, and in some cases, extorted for money under copyright laws? Yes, where are those copyright laws now? Why are courts and governments now giving a free pass to filthy rich OpenAI, Microsoft, Google & Anthropic? I hate everything about this dual treatments. These AI companies even have audacity to tell others their AI output is copyrighted & others can't use it
Occult cyberpunk. Yap with me about decentralized systems, wearable computing, and biohacking.