Jev-like decisions from open LLMs
Anand Prasad explains how to get Jev-like fast decisions out of low-cost open-source LLMs with no training, and how an LLM scores its vocabulary to pick the next word.
XNot a typed-decision job: needs written output, plain rules or lookups would do it, or needs raw image or audio. Also marks ideas that must not be built.2.76
Key facts
- Vertical
- Software & tech
- Function
- Agents & dev
- Status
- Seen in the wild
- Volume
- occasional
- Value
- minor
- Risk
- low
- Evidence
- described plan
- Flags
- None
Source: https://madewithjev.com/builds/jev-like-decisions-from-open-llms
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “Jev-like decisions from open LLMs”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.