A browser step from 2 s to 0.2 s
Accuracy dropped by six percentage points, which the post reports rather than hides.
CA clean typed decision with low volume or low value, or too vague to act on.2.22
Key facts
- Vertical
- Unclassified
- Function
- Agents & dev
- Status
- Seen in the wild
- Volume
- occasional
- Value
- minor
- Risk
- low
- Evidence
- built and shown
- Flags
- None
Source: https://madewithjev.com/builds/browser-agent-2s-to-02s
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 “A browser step from 2 s to 0.2 s”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.