AI Safety Watchdog Robot Checks Risky Actions
A robot called VIGILIA watches AI behavior and logs risky actions for review
AA clean typed decision (yes/no, a pick from a list, or a level on a scale) that is concrete, repeats routinely, and has meaningful value.5.40
Key facts
- Vertical
- Software & tech
- Function
- Agents & dev
- Status
- Seen in the wild
- Volume
- high
- Value
- major
- Risk
- moderate
- Evidence
- described plan
- Flags
- check-fit
Source: https://madewithjev.com/community/gregorio-here-quick-one-for-the-people-trying
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 “AI Safety Watchdog Robot Checks Risky Actions”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.