{"data":{"id":242,"backendId":"3d5d9b5e-7868-471a-8824-2f0a472d79fa","title":"Don't classify. Hallucinate!","summary":"<p><strong><a href=\"https://softwaredoug.com/blog/2026/08/10/hypothetical-classifications\">Don&#x27;t classify. Hallucinate!</a></strong></p>\nI still have quite a bit of older content on my blog that I never got round to tagging. My blog has <a href=\"https://simonwillison.net/\">1,856 tags</a> - likely too many to feed to an LLM in one go and say \"which of these tags match the following content\".</p>\n<p>Doug Turnbull has a neat solution. Tell the model to output tags without any details of the ex","analysis":"[NO_AI mode] 沿用 documents 表已有评分 (local-score 写回)","category":"technology","strategicTrack":null,"capitalRelevance":{},"tags":["AI","LLM","vector","embedding"],"qualityScore":10,"valueScore":10,"interestScore":10,"potentialScore":10,"uniquenessScore":10,"sourceCount":1,"confidence":5,"detectedAt":"2026-08-15T00:00:56.281Z","createdAt":"2026-08-15 00:01:09"}}