News updates

Show HN: AURA – Open-source behavioral threat detection for LLMs https://ift.tt/qVNDYS1 September 21, 2026 at 10:35PM

Show HN: MidiSlayer, a desktop sight-reading trainer for MIDI keyboards https://midislayer.com/ September 20, 2026 at 10:48PM

Show HN: Jev filters large HN discussions https://ift.tt/1fGYKBH September 20, 2026 at 10:37PM

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/NWylPDS September 20, 2026 at 01:10AM

Show HN: CUA-S1 – A System One Model for Computer Use Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possib...

Show HN: 3D map of which newsletters link to the same things https://ift.tt/y89c4I2 September 19, 2026 at 11:25PM