A Tale of Two AI Failures: Debugging a Simple Bug with LLMs
(news.ycombinator.com)
781.
782.
Effective harnesses for long-running agents
(news.ycombinator.com)
783.
Codex, Opus, Gemini try to build Counter Strike
(news.ycombinator.com)
784.
Show HN: Runprompt – run .prompt files from the command line
(news.ycombinator.com)
785.
786.
787.
788.
Claude Advanced Tool Use
(news.ycombinator.com)
789.
790.
Anthropic releases Opus 4.5 with new Chrome and Excel integrations
(techcrunch.com)
792.
793.
794.
With new Opus 4.5 model, Anthropic’s Claude could remain the best AI coding tool
(feeds.feedburner.com)
795.
796.
Claude Opus 4.5
(news.ycombinator.com)
797.
798.
Opinion | The First Large-Scale Cyberattack by AI
(feeds.content.dowjones.io)
799.
73% of AI startups are just prompt engineering
(news.ycombinator.com)
800.
801.
Measuring political bias in Claude
(news.ycombinator.com)
802.
Measuring Political Bias in Claude
(news.ycombinator.com)
803.
Google's Gemini 3 is living up to the hype and creating games in one shot
(bleepingcomputer.com)
804.
Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark
(news.ycombinator.com)
805.
Nvidia, Microsoft and Anthropic Commit to Roughly $45 Billion in AI Partnership
(feeds.content.dowjones.io)
806.
808.
Show HN: Continuous Claude – run Claude Code in a loop
(news.ycombinator.com)
809.
Structured outputs on the Claude Developer Platform
(news.ycombinator.com)
810.
Structured Outputs on the Claude Developer Platform (API)
(news.ycombinator.com)