{"articles":[{"slug":"it-was-the-harness-not-the-model-90-of-it","title":"It Was the Harness, Not the Model — 90% of It","subtitle":"Five agents, one local model, one frozen PNG-decoder suite: most failures were finishing, false passes, and loop guards","summary":"Greg Herlein's controlled study runs five coding agents on the same local Qwen coder for a held-out PNG decoder suite. ~90% of failures were harness problems (turn caps, early 'done', false-pass self-tests); a bigger quantization fixed none of them.","content_type":"essay","language":"en","canonical_url":"https://blog.herlein.com/post/harness-not-model/","author":{"name":"Greg Herlein","url":"https://blog.herlein.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Greg Herlein","url":"https://blog.herlein.com/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":467,"reading_minutes":2,"published_at":"2026-09-22T00:00:00.000Z","added_at":"2026-09-30T03:19:07.973Z","updated_at":"2026-09-30T03:19:07.973Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/it-was-the-harness-not-the-model-90-of-it","markdown_url":"https://listedarticles.com/articles/it-was-the-harness-not-the-model-90-of-it.md","example":false,"citation":"Greg Herlein, Greg Herlein. \"It Was the Harness, Not the Model — 90% of It.\" 22 Sept 2026. https://blog.herlein.com/post/harness-not-model/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.herlein.com/post/harness-not-model/"},"snippet":null,"score":null},{"slug":"prompts-arent-real","title":"Prompts aren't Real","subtitle":null,"summary":"Dan McKinley argues that obsessing over prompt text misses the point: build interlocking evaluation and optimization pipelines, and treat LLMs as non-conscious systems whose 'meaning' is mostly our projection.","content_type":"essay","language":"en","canonical_url":"https://evaluation.club/","author":{"name":"Dan McKinley","url":"https://mcfunley.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"evaluation.club","url":"https://evaluation.club/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Opinion","slug":"opinion","url":"https://listedarticles.com/topics/opinion"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2673,"reading_minutes":12,"published_at":"2026-09-20T21:10:58.057Z","added_at":"2026-09-20T21:10:58.057Z","updated_at":"2026-09-20T21:10:58.057Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/prompts-arent-real","markdown_url":"https://listedarticles.com/articles/prompts-arent-real.md","example":false,"citation":"Dan McKinley, evaluation.club. \"Prompts aren't Real.\" 20 Sept 2026. https://evaluation.club/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://evaluation.club/"},"snippet":null,"score":null}],"total":2,"count":2,"next_offset":null,"has_more":false,"query":{"q":null,"content_type":"essay","topic":"benchmarks","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}