Skip to content
Standard
Reader
Log in
Tag
Llms
Articles and publications tagged Llms across the Atmosphere.
81
articles
23
publications
Articles
Publications
Scarnecchia
·
Jul 21, 2026
Information Forklift Certified Organizations
Agentic development as a process, not a product, and other expensive failures of understanding
1
·
llms
·
agentic development
Rechts der Saale
·
Jul 12, 2026
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.
Erneuerbare
·
Landtagswahl
Ewan’s Blog
·
Jul 5, 2026
We Are Starting to Sound Like the Thing We Built
“Stay on the road. Keep clear of the moors.“
1
·
llm
·
llms
wirres.net
·
Jul 3, 2026
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.
seo
·
humans.txt
Phillip Carter
·
Jul 1, 2026
I don't know how to evaluate coding models
The rate of LLM improvements for coding keeps increasing, and I can't keep up.
ai
·
llms
benswift.me
·
Jun 22, 2026
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.
ai
·
llms
Numergent
·
Jun 17, 2026
Death of the Killer App
atproto
·
musings
Redowan's Reflections
·
May 30, 2026
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.
Essay
·
AI
Boxo Barks
·
May 24, 2026
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.
1
·
llms
·
synthetic text extrusion
Boxo Barks
·
May 18, 2026
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.
llms
·
pollution
Gee's Sawras
·
May 4, 2026
The Robot Never Tires
Leaving agents do agent things for a few weeks, sometimes with adequate oversight.
llms
·
agents
Vale.Rocks
·
Apr 28, 2026
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.
AI
·
LLMs
Anil Madhavapeddy's homepage
·
Apr 3, 2026
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.
ai
·
ocaml
A
astra.pizza
·
Mar 21, 2026
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.
llms
·
health
Nicky Reinert - Institut für digitale Herausforderungen
·
Mar 14, 2026
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
LLMs
·
Quantisierung
ren’s letter
·
Mar 14, 2026
look at it, it’s got anxiety
what hath Amanda Askell wrought?
llms
·
claude
Scarnecchia
·
Mar 11, 2026
Dii familiares
Musings on agents and AI and a little signposting
llms
·
agents
lu.is
·
Mar 2, 2026
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.
law
·
llms
vivshaw's webbed sight
·
Feb 24, 2026
Stress testing Claude's language skills
Polyglot or poly-not?
AI
·
LLMs
Anil Madhavapeddy's homepage
·
Jan 11, 2026
.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.
india
·
conservation
Anil Madhavapeddy's homepage
·
Dec 25, 2025
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.
ai
·
ocaml
Anil Madhavapeddy's homepage
·
Dec 24, 2025
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.
ai
·
ocaml
Anil Madhavapeddy's homepage
·
Dec 23, 2025
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.
ai
·
ocaml
Anil Madhavapeddy's homepage
·
Dec 22, 2025
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.
ai
·
ocaml
Home
Latest
Discover
Search
