AIの余計な一言に悩んでいませんか?「Vomit」に学ぶ、プロンプトエンジニアリングによる出力クリーンアップ設計ガイド
Article URL: https://github.com/zachahn/vomit Comments URL: https://news.ycombinator.com/item?id=49375996 Points: 195 # Comments: 209
Article URL: https://github.com/zachahn/vomit Comments URL: https://news.ycombinator.com/item?id=49375996 Points: 195 # Comments: 209
My hypothesis is that there is a new opportunity for Extensible Software on the web. LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and
Article URL: https://github.com/vixhal-baraiya/microgpt-c Comments URL: https://news.ycombinator.com/item?id=49347477 Points: 106 # Comments: 32
https://xcancel.com/kuberwastaken/status/2089377982536388964
Article URL: https://www.onethousandmeans.com/p/norway-should-buy-openai Comments URL: https://news.ycombinator.com/item?id=49351330 Points: 130 # Comments: 136
Article URL: https://www.npr.org/2026/08/18/nx-s1-5929575/ai-suicide-risks-mental-health Comments URL: https://news.ycombinator.com/item?id=49346002 Points: 1 # Comments: 0
Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.6 Luna (max), and just one point behind GLM-5.2 (max) and DeepSeek V4 Pro 0813 (max) - that GLM is 7
Article URL: https://openrouter.ai/openai/gpt-5.6-sol Comments URL: https://news.ycombinator.com/item?id=49337602 Points: 167 # Comments: 97
Hi HN! I'm Bek, founder of Speko, a platform that finds an optimal combination of speech-to-text, LLM, and text-to-speech models, given your constraints, among all our public benchmarked options,
Article URL: https://blog.roboflow.com/openai-gpt-5-6/ Comments URL: https://news.ycombinator.com/item?id=49329575 Points: 127 # Comments: 67