Orca-Bench: How Ready Are Language Model Agents for Oncall?
(news.ycombinator.com)
1.
3.
Show HN: What 180k words look like as a temporal knowledge graph (Oz series)
(news.ycombinator.com)
4.
Pseudpocalypse
(news.ycombinator.com)
5.
Are readers generating fiction with AI models?
(news.ycombinator.com)
6.
Knowledge Distillation of Black-Box Large Language Models
(news.ycombinator.com)
7.
Why Does a Bank Need a Chief Scientist?
(spectrum.ieee.org)
8.
Before You Add AI to Your Product, Ask These 7 Questions
(feeds.feedburner.com)
9.
Will AI spark a scientific renaissance — or a diffuse monoculture?
(feeds.nature.com)
10.
11.
Investigating how prompt politeness affects LLM accuracy (2025)
(news.ycombinator.com)
12.
Prompt Politeness Affects LLM Accuracy
(news.ycombinator.com)
13.
LLMs corrupt your documents when you delegate
(news.ycombinator.com)
14.
15.
Let's Talk about LLMs
(news.ycombinator.com)
16.
17.
Workspace Agents in ChatGPT
(news.ycombinator.com)
18.
Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
(news.ycombinator.com)
19.
The future of everything is lies, I guess: Work
(news.ycombinator.com)
20.
The Future of Everything Is Lies, I Guess: Work
(news.ycombinator.com)
21.
GLM-5.1: Towards Long-Horizon Tasks
(news.ycombinator.com)
22.
Qwen3.6-Plus: Towards real world agents
(news.ycombinator.com)
23.
Qwen3.6-Plus: Towards Real World Agents
(news.ycombinator.com)
24.
Chat GPT 5.2 cannot explain the German word "geschniegelt"
(news.ycombinator.com)
Today's top topics:
apple
openai
google
microsoft
samsung
amazon
android authority
iphone
android
trade secrets