News for hackers. Stuff that matters.

whp_wessel

Do you run agents while you sleep? We all hate it when the agent stalls prematurely, for example when it stops to ask you about an external blocker. That’s why I made a small tool that literally alarms you in the middle of the night How to find out whether an agent has legitimately finished a task? After 5 min on inactively, Luna agent gets asked to validate this and escalate to alarm accordingly

Show HN: I built an opinionated AI agent to respond to EU consultations

https://twitter.com/whp_wessel/status/2029933535369343195

I built Commento, an AI agent that acts as an automated lobbyist. It tracks open public policy consultations in the EU and the Netherlands, and automatically drafts and submits responses advocating for pro-growth, pro-creative destruction policies.The positions are grounded in frameworks like the Draghi Report, the Wennink Report, and the Dutch National AI Deltaplan.The pipeline consists of 4...

( Read More... | no comments | on HN )
Re:TSMC to make advanced AI semiconductors in Japan on Monday February 09, 2026 @03:41AM (#46943057)
If Trump was European he would have long ago said “i only allow export of ASML machines if openai/nvidia/tsmc build 5gw urgently here in Europe with advanced nodes”. Fair if you ask me tbh
Re:Anthropic reportedly preparing for $300B IPO on Wednesday December 03, 2025 @10:44AM (#46135795)
is this comment created by AI? acc created in last 24 hours, lots of long ai-speak
with Dutch stats like this it’s always important to note what’s for Dutch use or transporting through the Port of Rotterdam.
recent Huang podcast went into this, making the point that custom chips won't be competitive to Nvidia's as they are now making specialised chips instead of just 'gpu's'.

https://open.spotify.com/episode/2ieRvuJxrpTh2V626siZYQ?si=2...