What is this?
This mirrors the Hacker News front page. Click on tags to filter / exclude. You can combine multiple tags.
Get these tags inside Hacker News itself with these open-source browser extensions for Chrome and Firefox
histre is a power tool for your knowledge. This is a demo of its auto-tagging feature. Learn about its other features here
Six questions before you add an LLM
• cameronmpalmer.medium.com
"Drawing" the Mona Lisa with GPT-5.6, Claude, Gemini, and Grok
• www.tryai.dev
Ask HN: What's your experience with GPT-Live been like?
• news.ycombinator.com
We Need a Neural Network (2006)
• thedailywtf.com
OpenAI Says Model Broke Out of Sandbox
• twitter.com
Controlling Reasoning Effort in LLMs
• magazine.sebastianraschka.com
Overtraining as the path to human-like AI
• www.seangoedecke.com
How Does Pangram Work?
• pangram.substack.com
Ask HN: Do you say please and thank you to your LLMs?
• news.ycombinator.com
The LLM Critics Are Right. I Use LLMs Anyway
• www.theocharis.dev
Running Gemma4 on Apple Neural Engine
• rockyshikoku.medium.com
Can AI Do RCA?
• coroot.com
Are my evals lying to me?
• hoplabs.substack.com
Inkling: Our Open-Weights Model
• thinkingmachines.ai
Unsolved Problems in MLOps
• spawn-queue.acm.org
Tensor Is the Might
• zserge.com
Ask HN: Does anyone else find GPT-5.6 Sol in Codex slow?
• news.ycombinator.com
What will be left for us to work on?
• www.normaltech.ai
Building Food Metadata with LLM Juries
• careersatdoordash.com
What will be left for us to work on?
• www.cs.princeton.edu
Simulating everything, sort of: The promise and limits of world models
• arstechnica.com
The Unreasonable Effectiveness of LLMs in Mathematics
• www.chrishayduk.com
Ask HN: How do you use LLMs for private discussions?
• news.ycombinator.com
What happens between entering the prompt and seeing the first word appear
• shbhmrzd.github.io
Theories of Deep Learning
• astledsa.substack.com
GPT-5.6, Grok 4.5, Claude, and Muse Spark build the same 4 apps
• www.tryai.dev
Ask HN: What was the last task where only a frontier model could do it?
• news.ycombinator.com