First screen, captured .
Looks similar
Related stories
SkillsBench: Benchmarking how well agent skills work across diverse tasks(arxiv.org)
333 points by mustaphah | 142 comments
arXiv paper presenting SkillsBench, a benchmark of 86 tasks across 11 domains measuring whether structured Agent Skills improve LLM agent performance.
Spending 10 months building the most human-like chess bot(mbuffett.com)
29 points by marcusbuffett | 10 comments
A blog post by Marcus Buffett describing ten months spent building a chess bot designed to play like a human.
Tokens are getting more expensive(ethanding.substack.com)
341 points by admp | 230 comments
Substack essay by Ethan Ding arguing that AI token usage costs are rising and cheaper models won't save consumer AI subscription margins, citing Claude Code and Windsurf.
Writing "/etc/hosts" breaks the Substack editor(scalewithlee.substack.com)
604 points by scalewithlee | 327 comments
Blog post describing how typing the path /etc/hosts in the Substack editor triggers a network error, likely due to a web application firewall filtering rule.
After two years of vibecoding, I'm back to writing by hand(atmoio.substack.com)
747 points by mobitar | 544 comments
A Substack essay by Mo explaining why, after two years of relying on AI-assisted vibecoding, the author returned to writing code by hand.
Recent AI model progress feels mostly like bullshit(lesswrong.com)
474 points by paulpauper | 375 comments
LessWrong linkpost essay arguing recent AI model improvements feel overstated, based on experience building an AI codebase security-scanning startup.