The AKD1500 can use its own prediction errors to gate teaching. In this live repeat of a fixed binary-stream test, it opened 2 of 48 teaching gates and recovered both changed answers. Always-teach opened 48; cutting the gate or disabling learning kept the old answers. Holding history fixed caused errors.
Numbers
One synthetic stream of 48 next-bit predictions, with the rule changing two answers after step 16, run under five conditions:
| Condition | Teaching gates opened | Changed answers on revisit (steps 26, 27) | Errors before change |
|---|---|---|---|
| Error-gated teaching | 2 of 48 (steps 18, 19) | both right | 0 |
| Always teach | 48 of 48 | both right | 0 |
| Teaching gate cut | 0 of 48 | both old answers | 0 |
| Learning disabled | learning off | both old answers | 0 |
| History held fixed | 15 of 48 | both right | 7 |
Every output and every measured memory snapshot in all five conditions matched the earlier physical run byte for byte. The earlier study ran six preselected synthetic streams; error-gated teaching opened 2 of 48 gates and recovered both changed answers in all six.
The part worth knowing
In the error-gated condition, the teaching gate opens only when the prediction and supplied observation disagree. It recovers the same changed answers as always-teach, with 2 gate openings instead of 48. The short history and comparison run as programmed circuits on the chip; the host supplies the stream, initializes the rule and reads results back.
Limits
- We supply the stream, the starting history and the initial rule. The history and error circuits are programmed on the chip, not learned.
- This is a repeat of one previously tested synthetic stream, not a new task or a representative sample.
- Gate openings are not connection writes: error-gated and always-teach each changed connections twice in the reference trace.
- No timing advantage and no energy saving is claimed or measured.
Evidence and availability
- The November release notes describe the original six-stream study (prediction-error gated teaching).
- The run record, raw readbacks and independent recount are kept with the lab's internal audit; the video above is a transcode of the complete certified screen-recording master, with no cuts or added overlays.