Stories by al-fr-ed

Show HN: CleanMyMedia – organize decades of photos, with local face recognition

GLM-5.3 (open-weight) beat Anthropic/OpenAI models – for 1/5 the cost

Therapy Needs to Get Help

Building the Ed-O-Meter: Notes on Writing My Own LLM Benchmark

MCP and A2A are not solving one crucial challenge in the post-AGI world – Trust

Kimi K3 and GLM 5.2 can create undetectable malware for $2

We're getting closer to a breakthrough on hearing loss

Wp2shell-detect, a non-intrusive detector for the WordPress core pre-auth RCE

"It's Hard to Eval" Is a Product Smell

Burpwn – Burp Suite but its for AI agents (it works)

A system programmer's guide to LLM inference

How the modern world turned gray (and why color may be coming back)

Deterministic Simulation Testing for Distributed Systems: Good, Bad, and Ugly

Privacy Claims Token (PCT) – data obligations that travel with data

Show HN: Elia – A governed cognitive architecture (Phase 0 live)

Show HN: GAAI – One agent plans, one codes. A Markdown folder governs both

Show HN: Elia – Governed hybrid architecture (LLM is capability, not authority)

Evals Skills for Coding Agents

Schedule Recurring Tasks in Cowork

Prompt Injection = 100% Unbeatable – Try for Yourself

1 2 3 4 5 6 7 8 9 10