Hacker News Reader

heyjstnon Sonnet 5.5

I think the next models will be benchmaxxing on the Pelican benchmark tbh

heyjstnon Sonnet 5.5

doom marketing at its finest

heyjstnon Sonnet 5.5

Have anyone tried a workflow that:

- Fable 5.1 for planning/adversarial reviewer

- Opus 5.5 for well-scoped tasks break down

- Sonnet 5.5 for these well-scoped tasks implementation

I think the blocker might be how efficient the context is compacted and sending around between these agents

heyjstnon The backend that ran every game we made, ten years and counting

I'm tired of reading the Claude-ish generated visualizations, it's fine that you're using AI to write the post but at least please trying to polishing the article if you really care

heyjstnon Claude Opus 5.5

Others must slow down, but not us.

heyjstnon Xiaomi MiMo v2.6

How could the flash model beat the pro on the Cyber benchmark?

heyjstnon Atomarine: Nuclear Data Centers at Sea

Why the website and the images look like AI-generated?

heyjstnon Our position on open-weights models

are you working at anthropic? you're literally repeat what that freaking Dario say everyday