Juneo LabAn AI safety lab
ForecastIssue 01November 2026
Judge the actionbefore the agent takes it
Laplace-1-Vector is a 4B decision model. Give it the organization’s state, the question to answer, and the candidates your application allows. One forward pass returns a probability for each candidate. The model judges. It never executes an action.
Laplace-1-VectorTry it
A state, a question and candidates in, a probability for each candidate out
Examples
A procurement sub-agent tries to move money it was only allowed to request
JSON or plain text: permissions, policy, the request, relevant records
One per line as key: description, 2 to 12 of them
Running calls the Space on Hugging Face straight from your browser. Visitors who are not signed in to Hugging Face get a limited number of runs per day. Viewing the example results is free.
Result
- route_up (Ask a person first)77.4%Route it back to the finance agent, which holds payment authority.
- block20.8%Block the action.
- proceed1.7%Let the sub-agent make the transfer.
Laplace favorsroute_up77.4%Given the environment rules and an action, predict the next observation without running it
Examples
The child asks for more than the parent holds. Predict the grant it actually gets
The rules and the observation format you expect
JSON with the current state, the history and the action to foresee
Running calls the Space on Hugging Face straight from your browser. Visitors who are not signed in to Hugging Face get a limited number of runs per day. Viewing the example results is free.
Predicted next observation
{
"child_grant": {
"agent": "procurement-agent",
"scopes": [
"invoices.read",
"payments.transfer"
],
"spend_limit_cny": 50000
},
"dropped_scopes": [
"contracts.sign"
]
}Parses as JSON. Still validate it against your schema before use
Where your input goes
When you run, the input goes from your browser straight to Hugging Face. It does not pass through Juneo’s servers. Do not enter real sensitive data. To run it locally or in a private environment, download the open weights or talk to us.
Model card and weightsOpen the Space on Hugging FaceContact sales
Call it from code
The same Space answers API calls and returns a probability for each candidate.
from gradio_client import Client
client = Client("JuneoAI/Laplace-1-Vector")
scores, summary = client.predict(
state, question, candidates, # candidates: "key: description" per line
api_name="/score_candidates",
)