LLMs aren't world models
(news.ycombinator.com)
481.
482.
Can modern LLMs count the number of b's in "blueberry"?
(news.ycombinator.com)
483.
Evaluating LLMs Playing Text Adventures
(news.ycombinator.com)
484.
I tried coding with AI, I became lazy and stupid
(news.ycombinator.com)
485.
The current state of LLM-driven development
(news.ycombinator.com)
486.
Programming with AI: You're Probably Doing It Wrong
(news.ycombinator.com)
487.
Achieving 10,000x training data reduction with high-fidelity labels
(news.ycombinator.com)
488.
An LLM does not need to understand MCP
(news.ycombinator.com)
489.
Blocking LLMs from your website cuts you off from next-generation search
(news.ycombinator.com)
490.
LLM Inflation
(news.ycombinator.com)
491.
Five ways that AI is learning to improve itself
(technologyreview.com)
492.
Ask HN: What trick of the trade took you too long to learn?
(news.ycombinator.com)
493.
Do LLMs identify fonts?
(news.ycombinator.com)
494.
495.
Show HN: Mcp-use – Connect any LLM to any MCP
(news.ycombinator.com)
496.
497.
Developing our position on AI
(news.ycombinator.com)
498.
Working on a Programming Language in the Age of LLMs
(news.ycombinator.com)
499.
Writing is thinking
(news.ycombinator.com)
500.
Writing Is Thinking
(news.ycombinator.com)
501.
502.
Show HN: Any-LLM – Lightweight router to access any LLM Provider
(news.ycombinator.com)
503.
Show HN: Any-LLM – lightweight and open-source router to access any LLM Provider
(news.ycombinator.com)
504.
Any-LLM: A unified API to access any LLM provider
(news.ycombinator.com)
505.
Show HN: Intercepting proxy for semantic search over visited pages
(news.ycombinator.com)
506.
Coding with LLMs in the summer of 2025 – an update
(news.ycombinator.com)
507.
508.
Rethinking CLI interfaces for AI
(news.ycombinator.com)
509.
Local LLMs versus offline Wikipedia
(news.ycombinator.com)
510.
I avoid using LLMs as a publisher and writer
(news.ycombinator.com)