Andy Konwinski(@andykonwinski):sure you can use an LLM to do your semantic embedding. it's only 1000x more expensive and slower. the bigger question is: how long before LLMs can do it better cheaper and faster? Will they ever?

Andy Konwinski

@andykonwinski

Co-founder of @laudeinstitute, @laudeventures, @databricks, @perplexity_ai

参加 July 2010

120 フォロー中 12.1K ファン

Andy Konwinski@andykonwinski

2026.08.20 15:16

sure you can use an LLM to do your semantic embedding. it's only 1000x more expensive and slower. the bigger question is: how long before LLMs can do it better cheaper and faster? Will they ever?

Adnan El Assadi@AdnanElAssadi

2026.08.19 20:37

Did LLMs finally subsume embedding models? We compared 10 LLMs vs. 26 embedding models across 37 MTEB tasks. LLMs scored 77.6 while embedding models scored 77.2 But the costs are very different. 🧵