Tag: AI

Posted on
by
Favorited I used AI. It worked. I hated it. by Michael Taggart

An excellent post by Michael Taggart on how it felt to him to make a much needed bit of code with the help of Claude Code. The results worked, but he hated how it made him feel. He explores those opposing outcomes without trying to resolve the tension. Much in here that I recognise from my own experiences, as well as what I see others do and how they talk about it. Towards the end he talks about ‘the real monster’ here, and I think that is the right frame: we have created a technology monster once more, and Smits’ monster theory (2003) is a tool to bring to bear again. Where will we adapt the monster to our tastes? Where will we shift our cultural understanding of ourselves and the world to make room for the monster? Once we’re done embracing it until the bubble bursts, or rejecting it outright no matter what.

I hated writing software this way. Forget the output for a moment; the process was excruciating. Most of my time was spent reading proposed code changes and pressing the 1 key to accept the changes, which I almost always did. I was basically Homer’s drinking bird.

Michael Taggart

Posted on
by
Favorited If you thought the speed of writing code was your problem – you have bigger problems by Andrew Murphy

Good blogpost on how ‘speeding up’ code production (x lines committed this week, yay!) by using AI, will likely cause more trouble in an organisation. Because the theory-of-constraints bottleneck in an organisation will never be the speed and volume of writing code.

For non-coders making personal tools, this is I think different.

When you optimise a step that is not the bottleneck, you don’t get a faster system. You get a more broken one.

Andrew Murphy

Posted on
by
Favorited Ollama Claude Code integration by Ollama
Favorited LM Studio Claude Code integration by LM Studio blog

Last Friday I participated in a workshop by Frank Meeuwsen on using Claude Code. I’ve been reluctant to use Claude Code for the basic reason that it uses cloud run models by default. This means that my inputs and any context I provide leave my machine to be gobbled up into the data foraging models. Nevertheless it was fun, I improved on my existing personal feed reader (a presentation layer on top of FreshRSS that allows me to write responses while I’m reading feeds).

However tempting it is to continue vibecoding with Claude Code and watching it work its way through my coding requests, that is not the way to go. After some online searching I found the above two pages, that explain how to point the program Claude Code to use the local end point of either Ollama or LMStudio. That’s more like it!

Now I need to figure out which LLMs that can be downloaded (or run on a VPS perhaps) are best suited to the type of tasks I want to set it. For coding, local agents, translation, and semantic work. There can be multiple models of course, as I can switch them up or run them sequentially (and in parallel if I deploy them on a VPS I think).

Open models can be used with Claude Code through Ollama’s Anthropic-compatible API

Ollama documentation

This means you can use your local models with Claude Code!

LM Studio blog

Posted on
by

Came across this 2025 book in a Bregenz book store, Brunner, last summer while visiting the Austrian alps, and later looked for it online.

Set in an ancient convent in a small deserted Italian village, and narrated by what appears to be a renaissance literary style all knowing voice. After a few chapters it becomes more apparent who the narrator is. Took me a bit to get into, because of that narrator, but then enjoyed it. Some nice ideas, funny at times, and entertaining.
Horváth is an Austrian writer, and this seems to be his third novel.

Read in German through the Kobo plus subscription.

Posted on
by
Favorited AI Village by AI Village

Four AI’s Claude Opus 4.5, Gemini 3 Pro, GPT-5.2, and DeepSeek-3.2 are brought together to form ‘a village’. They interact, can use a computer, and need to work things out between them. They get and set tasks (like ‘elect a village leader’) and spend the day going about it. The logs read like ironic slapstick. Bumbling forward all the time, not meeting self-set deadlines, messing up hand-offs and hand-overs of tasks. And they spend working days on it! That’s like years in computer time. Doesn’t sound much like the singularity-achieving super fast high efficiency we get promised that MS Office, sorry, Microsoft 365 Copilot, would achieve for us before our first coffee if we would just switch on AI.
It does seem these models have a great steady bullshit job going. So maybe that is a sign of the predicted looming mass lay-offs after we AI-all-da-things after all.

It made me laugh that the models are attributing their own faulty use of tools to ‘bugs’ in those tools. AI so human!

(h/t Stephen Downes)

They repeatedly blamed “bugs” in Google Docs and browsers for issues that were clearly their own misuse of tools

AI Village

Posted on
by

Thanks ChatGPT!
Commenting is open on this website, and that means being engaged in a permanent asymmetric battle against spam. Asymmetric in the sense that like on any social media platform it is multiple orders of magnitude easier to automatically create and send out spam, falsehoods and hate speech in extremely large volumes, than it is for actual people to weed those out of their timelines and websites.
Most of incoming spam filtering is automated away these days, but always some and especially novel types are left for me te moderate myself, as the arms race continues.

A new entrant in the spam battle are AI generated spam comments that have clearly been fed the content of the actual blogpost that is being commented. Like other spam they stand out due to their blandness, what they link to and that the same things get submitted multiple times from different origins, but they are building on the content itself. I guess I should feel flattered.

It is also logical, as both spam and AI generated material are based on the exact same asymmetry. ‘Efficiency’ gains through AI generated text, are at best only that at the generation end of things (now see me generate oodles of text in seconds!), yet increases the effort needed at the receiving end to read it, see through the veil of plausibility, verify it and judge it inadequate.


Two examples of AI generated spam comments using the content of the actual blog posts (here a recent week notes posting, and one about donating money for ebooks rather than spending it at Amazon.) One commenter giving ‘undetectable AI’ as their name is a bit of a give-away though.

Any comments on this site already are subject to a Reverse Turing test, with all received material deemed generated until determined created by a person. Clearly this is no longer just a precaution resulting from tongue-in-cheek cleverness, but a must-have part of my toolkit for online interaction.