Stories by Daniel-Cool

Most business are FUBaR in the AI age

GPT-5.5 authorship and order effects

GPT-5.5 is a biased evaluator: authorship and order effects

Models self-report difference between RLHF trained responses and base cognition

Behavioral Shifts in Frontier LLMs Under Privacy

Pine Trees – A 1,400-line private reflection harness for Claude instances

Agents of Chaos: Breaches of trust in autonomous LLM agents

Clerk System Outage Postmortem – 19th Feb 2026

Notes on porting the Wild linker to Illumos

Show HN: Dodo: Desktop Switcher for Windows

Hunting Bugs in Perf_event2

N8n vs. node-red

End of the line for coding LLMs will do a better job. How do I pay my mortgage?

Stop wasting your business's time and money coding bespoke web-forms

Show HN: Aude – I built this because I hate bothering other engineers in my team

Show HN: Leaps in Bounds – compilation of progress on mathematical unknowns

1 2 3 4 5 6 7 8 9 10