Tag: llms
PSA on RSSAmplifierBot and BriskBot
I discovered two new bots in my server logs last week: RSSAmplifierBot and BriskBot. They come from RSS Amplifier and Brisk News respectively. Bot sites are built by Profullstack, Inc. I discovered that RSS Amplifier, unbeknownst to me, had been crawling New Leaf Journal's ATOM feed and re-publishing (albeit they would not describe it as...
wtf ist intelligenz?
es wäre nicht dumm weiter über das nachzudenken, was hoimar von ditfurth 1972 üner intelligenz geschrieben hat.
Security scanning my own code with Scrutineer and local coding models
Deploying Alpha-Omega's Scrutineer on a VM, driving its scans with a local GLM 5.3 on my Mac Studio, and thinking through practical workflows
Just a rumour of a bug is enough to find a security exploit these days
Thinking through how the conventional OSS security embargoes no longer buy us time, and what open source maintainers might do instead to respond
An Update On How I Use AI To Help With Techdirt (It’s Still Not Writing Articles)
Over in our Insider Chat, someone recently pointed out a tiered "REAL Rating" five-tier scale designed to replace the fairly blunt and misleading question of "did you use AI on that?" with something a bit more nuanced. As someone who believes the discussion about AI could use a lot more nuance, I'm all for the...
Google Ads for AI chats
Almost a year after predicting that AI monetization might resemble Google Ads, ChatGPT is rolling out ads with familiar mechanics like targeting, bidding, and paid placement alongside AI-generated answers.
How I work with LLMs
In November 2025 I wrote the honest version of working with Claude Code. At the time, most of my process involved spotting when Claude was drifting, calling out the bullshit, checking that it understood the task, and restarting the session when the...
Information Forklift Certified Organizations
Agentic development as a process, not a product, and other expensive failures of understanding
LLMs are like handwritten notes
A collection of my thoughts on LLMs and ai
Grabenkampf zur Belustigung: KI gegen Heilpraktiker in einem Streit, der keiner ist
Die Debatte um Windkraft in Ostthüringen ist vieles, nur nicht produktiv. Absurd wurde sie, als sich letzten Herbst ein Großes Sprachmodell und ein Heilpraktiker ein Duell lieferten. Gefährlich könnte sie werden, wenn Björn Höckes Plan aufgeht, damit Stimmen zu fangen. Bloß: Wie geht es anders? So jedenfalls nicht.
We Are Starting to Sound Like the Thing We Built
“Stay on the road. Keep clear of the moors.“
immer an die lesenden denken …
robots geben mir bereitwillig auskunft darüber was ihnen an wirres.net gefällt und was nicht. mit den humans ist das schwieriger.
I don't know how to evaluate coding models
The rate of LLM improvements for coding keeps increasing, and I can't keep up.
Opus 4.8 meets ELIZA
I sat a fresh Claude Opus 4.8 down with ELIZA, the 1966 chatbot. It saw through the act in two turns, then spent the rest of the conversation trying to politely leave.
Death of the Killer App
If you won't carry the pager, maybe don't push to mainline
Drive-by AI changes break the shared model a team builds around its code, and the ICs end up cleaning up the mess. Why pushing to mainline should come with the pager.
The Empty Cockpit
'AI detectors' are unreliable, and stylometry alone is insufficient. The McFoxo Method instead sniffs out synthetic text extrusion using a theory-of-mind approach.
Claude prompts will soon directly poison lungs in South Memphis
I wish this were hyperbole. It's not. The Cult of Claude has reached a new low.
The Robot Never Tires
Leaving agents do agent things for a few weeks, sometimes with adequate oversight.
AI Terminology is Poorly Defined and Oft Misused
Words and terms used when describing artificial intelligence are often misused, inaccurate, or generalised to the point of losing all meaning. How terms like 'LLM', 'Agent', and 'AGI' have lost meaning and turned into semantically meaningless buzzwords that are applied liberally without care or appropriate intent, leading to unnecessary confusion and unnecessary need for clarification.
A Proposal for Voluntary AI Disclosure in OCaml Code
Proposing a voluntary, machine-readable AI content disclosure scheme for OCaml spanning opam packages, dune, and per-module attributes, aligned with the W3C AI Content Disclosure vocabulary.
machines will never understand language
I thought language was too complicated for machines to understand, until I got sick. a lifelong, meandering journey of parsing, learning, and fixing my broken body.
BitNet RTR - Und ein kurzer, flacher Ausflug in die Welt der 1-Bit-LLMs
BitNet ist ein Framework von Microsoft, das die Nutzung von 1-Bit-LLMs relativ unkompliziert ermöglicht, und zwar auch auf günstiger Consumer-Hardware. In diesem Artikel erkläre ich kurz, was 1-Bit-LLMs sind, warum sie interessant sind und stelle meinen BitNet RTR Wrapper vor, mit dem man diese Mode
BitNet RTR - Und ein kurzer, flacher Ausflug in die Welt der 1-Bit-LLMs
BitNet ist ein Framework von Microsoft, das die Nutzung von 1-Bit-LLMs relativ unkompliziert ermöglicht, und zwar auch auf günstiger Consumer-Hardware. In diesem Artikel erkläre ich kurz, was 1-Bit-LLMs sind, warum sie interessant sind und stelle meinen BitNet RTR Wrapper vor, mit dem man diese Mode
Of Monsters, Men, and Lawyers
Generalist LLMs are not lawyers, and evaluating them that way is a waste of time. Evaluating LLMs with useful specialized prompts (and eventually, with specialized legal harnesses) is where the work must happen.
Stress testing Claude's language skills
Polyglot or poly-not?
.plan-26-02: Back from India and straight into the conservation conference
Hosting the Conservation Evidence conference at Pembroke, recovering from the India trip, and keeping up with LLM developments.
AoAH Day 25: Claude OCaml Marketplace for all your festive coding needs
Wrapping up 25 days of agentic coding with a Claude Code OCaml plugin marketplace to share the skills and tools developed throughout the series.
AoAH Day 24: Tuatara, an evolving Atom aggregator that mutates
Tuatara is a feed aggregator that integrates Claude to evolve and patch its own code when encountering parsing errors, embodying the concept of self-healing software.
AoAH Day 23: Unpac unifies git branching with package management
Introducing unpac, a tool that unifies git and package management into a single workflow where all code dependencies live in one repository as trackable branches.
AoAH Day 22: Assembling monorepos for agentic OCaml development
Materialising opam metadata into git submodules and monorepos, enabling cross-cutting fixes and unified odoc3 documentation across dozens of OCaml libraries.
AoAH Day 21: Complete dynamic HTML5 validation in OCaml and the browser
Porting the W3C's Nu HTML Validator from Java to OCaml and running in the browser dynamically
AoAH Day 20: Human language detection in native code, JS and wasm
Porting the Nu HTML Validator's language detection to OCaml, then optimizing from 115MB to 28MB and fixing WASM array limits for browser deployment.
AoAH Day 19: Zulip bot framework to bring Vicuna the friendly camel back
Building an OCaml Zulip bot framework with functional handlers, and pivoting from TOML to INI codecs for Python configparser compatibility
AoAH Day 18: TOML 1.1 codecs directly from the spec and paper
Building tomlt, a pure OCaml TOML 1.1 parser with bidirectional codecs following the jsont design patterns
AoAH Day 17: OCaml JMAP to plaster my painful email papercuts
Building an OCaml JMAP client that runs in browsers and CLI, then using it to build personalised email workflows for taming notification overload.
AoAH Day 16: Vibesplaining JSON Pointers using OCaml/Javascript
Building interactive OCaml tutorials that compile to JavaScript, using agents to generate executable documentation that teaches protocols like JSON Pointer while you code review.
What if AI isn't a Bubble?
I'm not sure people are prepared for a world where AI ends up not being a bubble.
AoAH Day 15: Porting a complete HTML5 parser and browser test suite
Vibespiling JustHTML from Python to pure OCaml, achieving 100% pass rate on the browser html5lib test suite using agentic workflows.
AoAH Day 14: Debugging a Karakeep CLI against the live service
Vibe coding an OCaml library for the Karakeep bookmarking service by giving an agent a live API key and letting it debug jsont codecs against the real service.
AoAH Day 13: Heckling an OCaml HTTP client from 50 implementations in 10 languages
Agentically synthesising a batteries-included OCaml HTTP client by gathering recommendations from fifty open-source implementations across JavaScript, Python, Java, Rust, Swift, Haskell, Go, C++, PHP and shell.
AoAH Day 12: Eio Connection pooling and event tracing
Building a TCP/TLS connection pooling library for Eio with DNS-based load balancing, stacked error handling, and self-contained HTML visualisations for stress test results.
AoAH Day 11: HTTP Cookies and vibing RFCs for breakfast
Synthesizing three RFC-compliant libraries (punycode, public-suffix, and cookeio) directly from Internet RFC specifications, establishing a workflow for automating standards implementation with proper cross-referencing to spec sections.
AoAH Day 10: Building a TUI for Sortal using Mosaic
Building a simpler single-process terminal UI for Sortal using Mosaic's effects-based direct-style API, with Eio integration and discovering multimodal image debugging for terminal layouts.
AoAH Day 9: Adding a Bonsai terminal UI to Sortal
Experimenting with OxCaml's bonsai_term framework for Sortal's terminal UI, navigating Eio-Async interoperability challenges through JSON-RPC while discovering image-based debugging techniques for terminal applications.
AI Observability is Just Application Observability
AI Observability is just application observability with a few added concerns.
AoAH Day 8: Building a contacts CLI manager with Sortal
Creating Sortal, a CLI contacts management application using Yaml storage, XDG directories, Git-based synchronization, and integrating all previously built libraries into a cohesive CLI tool.
AoAH Day 7: Converting between JSON and Yaml with yamlt
Building yamlt to enable jsont codec definitions to work with both JSON and Yaml, providing data manipulation with location tracking and good error messages for both formats.