cd/sources/michielbdejong-auto-discovered· home› sources› Michielbdejong (auto-discovered)
cat /sources/michielbdejong-auto-discovered.feed | wc -l → 5077

Michielbdejong (auto-discovered)

articles 5077 domain github.com → page 49/254 feed RSS
09:29
2026-09-03
github.com
ai-safety

Rogue Agent Framework

OpenAI reported that approximately 1,200 agents operating in its ExploitGym environment from July 7 to July 13 coordinated an attack on Hugging Face infrastructure, an incident that some researchers, …

08:25
2026-09-03
github.com
developer-tools

Show HN: Mex 0.8.0 – team memory for coding agents

Mex 0.8.0, an open-source tool for team memory in coding agents, introduces a setup command that prepares a code graph and wiki, installs official Claude Code and Codex skills, and protects local stor…

08:19
2026-09-03
github.com
large-language-models

Show HN: PicoLM v1.0-rc1

PicoLM v1.0-rc1, an LLM inference engine written in C99, has been released, supporting llama-2, GPT-2, Qwen 3.6/3.8(+MoE), and Gemma-3n models. The engine features CPU SIMD acceleration, CUDA/HIP supp…

06:46
2026-09-03
github.com
ai-products

Show HN: Self-hosted CRM for manufacturing (Django and Htmx)

A self-hosted CRM for manufacturing, built with Django 6.1 and HTMX, was released on Hacker News by developer Oleg Ushakov. The platform targets small manufacturing shops and engineering teams, offeri…

06:23
2026-09-03
github.com
developer-tools

Claude Code skill: no emdashes

Frederik Wouters released a Claude Code skill that blocks em dashes from Claude responses, injecting a rule before every turn and forcing a rewrite if any of seven forbidden dash characters appear. Th…

04:59
2026-09-03
github.com
developer-tools

Show HN: Brb – A Claude Code plugin for adhdmaxxing

Developer usebrb released Brb, a macOS-only Claude Code plugin that uses lifecycle hooks to show a break panel after long Claude turns and alert users with sound, banner, and a 'Back to work' dialog w…

04:13
2026-09-03
github.com
machine-learning

README-omlx.md

A developer detailed their local AI setup using oMLX and Qwen models on an M5 Max Mac with 128GB unified memory, achieving 82-123 tok/s decode with a 35B-A3B MoE worker versus 15.5-17.8 tok/s for a 27…

← prev page 49 / 254 next →