Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
(news.ycombinator.com)
91.
92.
Amazon workers under pressure to up their AI usage are making up tasks
(news.ycombinator.com)
93.
Amazon workers under pressure to up their AI usage–so they're making up tasks
(news.ycombinator.com)
94.
Amazon workers are under pressure to up their AI usage—so they’re making up extraneous tasks
(feeds.feedburner.com)
95.
Most products work, few work well
(feeds.feedburner.com)
96.
97.
98.
OpenAI Codex brings agent AI workflows to coding tasks
(techspot.com)
99.
100.
101.
102.
103.
104.
105.
107.
A Git helper tool that breaks large merges into parallelizable tasks
(news.ycombinator.com)
108.
Human scientists trounce the best AI agents on complex tasks
(feeds.nature.com)
109.
110.
GLM-5.1: Towards Long-Horizon Tasks
(news.ycombinator.com)
111.
For Everyday Business Tasks, This $200 Refurbished MacBook Air Gets It Done
(feeds.feedburner.com)
112.
113.
114.
Issue: Claude Code is unusable for complex engineering tasks with Feb updates
(news.ycombinator.com)
115.
Claude Code is unusable for complex engineering tasks with the Feb updates
(news.ycombinator.com)
116.
StepFun 3.5 Flash is #1 cost-effective model for OpenClaw tasks (300 battles)
(news.ycombinator.com)
117.
Fantastical can now trigger alarms for events and tasks
(9to5mac.com)
119.
Schedule tasks on the web
(news.ycombinator.com)
Today's top topics:
openai
anthropic
apple
ai safety
google
iphone 18 pro
artificial intelligence
ios 27
dario amodei
nvidia