-
The AI Layoff Wave, 2023–2026: How It Moved in Step
From ChatGPT bans to AI-first memos to the biggest AI-labelled cuts: how the 2023–2026 wave was synchronized through memos, investors, consultants and peer imitation, what AI really did, and what the record does and doesn't show.
-
594,101 knocks: who reads my site, and what AI crawlers can't see
AI systems read my site 1.5x as often as search engines and 58x as often as Google, mostly my signed threat-intel dossiers. One crawler hit my login page 594,101 times. What is public is the small part.
-
Why I went fully local: from cloud AI to a sovereign lab at home
In April 2026 my AI setup mixed slow local models with cloud ones. By October everything that runs, stores or decides was local. The library-scale arithmetic, the test that ended the argument, and the one exception I still keep.
-
13 hours of question marks: a canary for LLMs that look healthy
After a llama.cpp router restart my main model answered every request with question marks for 13 hours while every health check stayed green. A known-answer canary now catches it within 10 minutes.
-
How small local models finish hour-long agent tasks
Left alone, my 9B agent closed tasks without doing them and invented a 10 KB report from an empty sub-agent result. Scaffolded task trees, evidence checks and deterministic gathering let it finish 66-minute projects.
-
One GPU, many LLMs: the VRAM guards that stopped a driver deadlock
With 33.9 of 34.2 GB of VRAM in use, a desktop app triggered a 24.7 GB eviction and froze my GPU driver. Here is the VRAM budget and the two guards that now enforce it.
-
Local AI study guides for thousands of books, capped on purpose
Hosted study guides cost 80k tokens per part, so I moved to a local 4B model. What broke, the guardrails that fixed it, the 100-chunk and 60-section caps, and why breadth beat depth.
-
From Ollama to a llama.cpp router: 49 models down to a few presets
I replaced Ollama with a llama.cpp router on my home-lab GPU: on-demand presets, sleep timers, embedding parity tests, and a log-driven retirement that freed about 400 GB.
-
Vision-model OCR that keeps the layout: what to trust it with
A vision model called a bold italic paragraph 'not bold, not italic'. My OCR now lets the model read, Tesseract place small text, and pixel measurement judge typography: 99% precision on italic words.
-
Why local LLMs could not drive an autonomous pentest agent
I tuned an autonomous security-testing agent until the mechanics were clean, then watched my local 27B model read 1.44 million tokens and find none of three planted bugs. Here is how to separate fixable plumbing from a model that cannot do the job.
-
Translating whole books with local LLMs: the failure modes
My local translation service rebuilds scanned books page by page in another language. Most fixes were not about the model: segment context, glossary scope, a lost-update race and page rebuilding.
-
Typed decisions from logits: LLM judgements that cannot fabricate
Reading a 9B model's option probabilities instead of its text took a disambiguation task from 22.7% to 86.7%, added a usable confidence, and removed fabricated reasons. Most of the gain was wording.