Don't Call It a Decision Model
emschwartz
15 points
4 comments
November 04, 2026
Related Discussions
Found 5 related stories in 134.9ms across 11,645 title embeddings via pgvector HNSW
- Build your own decision model softwaredoug · 203 pts · October 10, 2026 · 65% similar
- Microsoft-Decision-1, our model for fast decision-making lisajaloza · 174 pts · October 09, 2026 · 63% similar
- Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers tomncooper · 24 pts · October 02, 2026 · 58% similar
- Strands Decider 2B: a small, open-source, decision model gmays · 107 pts · October 07, 2026 · 57% similar
- The most important product decision is what you don't build ChrisArchitect · 80 pts · September 17, 2026 · 54% similar
Discussion Highlights (3 comments)
edot
Drives me nuts that this nomenclature caught on. This (judgement, not decision) is a bit better. I mean, sure they (Jev-style models) are useful for zero-shot classification, but they're only "judgement models" insofar as any (LLM, ML, mathematical optimization, heuristic, etc.) model that sets a downstream float / integer / boolean to commit resources (read: makes a decision) is a "judgement model". https://warrenpowell.org/decisionsdecisions/ If you actually want to make good, even optimal (provably) decisions, try reading some about mathematical optimization, or operations research more broadly. The above link is a good place to start.
willio58
Really cool visual way to do demonstrate the point. Jev is so interesting to me, I just struggle to find good use cases in my work so far.
j45
I agree with this. Decisions/Judgements in LLMs are not logic gates like a deterministic piece of software, they are simulations cosplaying it more often than not. Depending on how it's worded it's pretty remarkable how much it can improve, but it ultimately is not deterministic.