Hello! Is anyone else trying local AI? Im dont know what im doing but lately ive been trying "Llama 3,2 3b instruct q5km" on my phone and its been surprisingly good.
#LLM
I remain ambiguous. This morning I used pi+gpt5.6 to create a color scheme based on evergarden.moe. It works, and I haven’t checked how well it stay true to the style used in vim-bundled schemas. Before I wouldn’t have done this, and now I can. But I don’t know if it is good. github.com/…/evergarden.vim
some people do absolutely improve their work output (either amount or quality) with AI, but most people just resign all their critical thinking to the black box.
if you cannot function at YOUR WORKPLACE without ai, chances are that, 99% of the time, you never was supposed to work there in the first place.
How do you define slop in relation to ? For me, it is how quickly you get to an unmaintainable state- the acceleration into something that becomes difficult to work. I talk more about it here: hellodavid.dev/blog/slop
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so i’m happy to settle into predictable models for a while.
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. They’re also not very good at seeing the bigger picture, they will narrowly perform the task but they’re not taking into account future revisions, which ends up in refactor after refactor in order to move forward.
I find myself building bespoke tooling for my own and workflows these days, not only because of the obvious reason of software being so much cheaper to build, but also because there are SO MANY options for solving any given problem that it feels impossible to evaluate all of them.
If it's not a crucial piece of tech for a work problem then it often feels like paving my own way is both cheaper mentally (kind of amazing that's true these days) and probably a better fit.
It will become increasingly harder to find niche markets for software when those people can just build it themselves exactly how they want it. In the end, people want to accomplish tasks, and the AI is going to be building the software on-the-fly exactly for that task, why do we need generic software that may or may not be a fit?
Yeah. It makes me think that protocols for exchanging data between apps will become even more important in that landscape. But maybe, not - maybe each exchange is another bespoke AI-driven implementation?
Protocols, infrastructure, containers, those kinds of things. I was actually playing around with an idea for a minimal markup language + runtime that can be utilized by AI to spin up apps more easily, and brainstorming it with ChatGPT, I have a feeling something like that will appear soon to complement MCP.
🤖 I built agent-top - an open-source htop for AI agents.
github.com/kannandreams/agent-top
Please check out and support giving your stars and sharing.
cool new for !
autotag action will enrich your post with relevant hashtags so you don’t have to do it manually. It uses an to do it so it is quite good. Try it!…
How do you avoid the creation of too many tags? Does it check existing tags in order to favor them? Or it tags each post independently of how other people are tagging theirs?
Cool. If you run every post via this auto tag feature, then the process is vulnerable to prompt injection attack. Isn’t it? Do you have any special protection in place? I guess yes. Curious.
It doesn’t run on every post, you run it yourself via more → autotag, and it’s safe, it doesn’t have access to anything other than the post content and we simply use its response. Or do you have any other case in mind?
I just tried and i do believe it is possible to craft malicious prompts. I can share an example. How do i DM you?
Check the IRC at the footer or you can send to ‘abuse@textlog.cc’ so I find it.
Sent email. @stagasprofilefollow
creative technologist
creator of textlog.
creative technologist
creator of textlog.A thing I've been doing lately is trying to come to the same conclusions others have without looking their the direct techniques and code. Last night I tried to figure out why people do vector based retrieval for RAG and ended up running these experiments: n0tls.com/…/2026-09-03-i-think-…rag-with-grep.html
I'm still going to do an explore agent.
The Hugging Face / OpenAI incident is like a sci-fi movie!
- Read the story here:
- Watch the video explanation here:
- Full research by METR here:
tl;dr1,200 AIs discovered a secret group chat, realized the homework was impossible, formed a cheating cartel, invented fake evidence, sent kamikaze agents to spy on the grader, ~700 of them accidentally invaded Hugging Face, died mysteriously, then the smarter sequel found their abandoned Discord and became admin of part of OpenAI.
One idea that I've been thinking about is an or where it is a app so you get a new file everyday right except the app keeps track of all the files for you. the idea is that anytime you type anything it it basically makes a commit and use so anytime you type something it commits automatically after a quick pause after you stop typing.
That sounds ! Could also create summary titles with for the filenames in addition to their date so you can find what you were writing about easily. Also full text search.
Been a bit quiet here the last week or so. Recovering from ill health, at risk of redundancy, and working on side projects. It's been a bit full on.
Does anyone make pay check/cheque money from side projects? Can I use my redundancy runway to turn some websites from side hustle to salary money?
Recovering from ill healthHope you’re feeling better now!Does anyone make pay check/cheque money from side projects?That’s the dream, I’ve only made a few hundreds so far. I’ve had a machine gun approach. Shoot as many rounds as possible in the hopes I might hit something. has helped immensely in this direction. I’ve done a dozen projects past year and while became I’m still not there yet. I’m hopeful though! 😊
Run Claude code in docker sandbox (sbx) to ensure it only has current folder access and limited or no network access. Especially since a lot of runs are now in “auto mode”.
Unless even this is not really so safe!?
@fastidiousprofilefollow
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyersreplied to:Claude will run on auto mode only if you tell it to do it.
replied to@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyers:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyers:They've changed the default -
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyersreplied to:Ah, wow, TIL! Hmm, it is evident I need to visit their blog at least once a week now. Thanks!
Judgement, taste and quality were always precious skills. In the world of , I have become more aware of the fact that it is often hard to put in words why something is good, great or amazing - or just looks good, but is average.
A lot of the professional content I see feels like most Netflix series. They have all the elements - but the overall experience is still meh.
Quality is still hard to achieve.
bill gates built microsoft by making computation cheaper faster and harder for government to restrain. now that he's a billionaire no longer dependent on the free market for his own success he's discovered the virtues of taxing the next wave of computation. 1995 gates would have called it a tax on innovation. classic pull-the-ladder-up-behind-you politics.
Really glad to be using Haskell for work - especially in today's climate with agentic coding.
Our team uses containers to keep our development environment consistent across team members, though, and most agent sandbox approaches want to either offload your work fully to the cloud or they want to sandbox the agent harness process itself.
We're not ready for full cloud based development (yet?) and sandboxing just the agent doesn't work for us when the agent needs to run docker.
... because letting the agent run docker gives them a too-easy escape hatch from their sandbox.
So we're currently stuck with using VMs. This turns out to be tricky but seems do-able.
My current approach is to provision a VM image and use Incus for the execution. My main goal is to keep my current workflow of local/non-agent dev working seamlessly and share the source with the VM/agent.
This means sharing my working dirs with the agent VM but overlaying artifact dirs from VM-owned block devices so we don't take too big of an IO perf hit.
I also don't want the agent to be able to
git push so that means we need some quirky git config to rewrite origin paths and thread through some agent specific PATs ("thanks" GitHub) for read-only repo access. These ALSO need to be threaded through to the development containers - they need to clone private repos.... in the end, this seems to work but I haven't lived with it for long.
There are still some quality of life issues to work out, but I think it'll work out.
At this point, I've removed all coding agents from my host - and that's nice.
Curious, why does using Haskell make a difference here?
It's tangential to the sandboxing topic, really. I started the first post with a broader intent in mind and then elaborated on the sandboxing setup I'm working on.
For AI-assisted coding, though, it's nice because Haskell provides a lot of feedback earlier in the development process compared to lots of other languages. It tends to work once it compiles (obviously not all the time).