Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,10 @@ tags:
|
|
| 18 |
|
| 19 |
> **Real-time reasoning failure detection in small language models via step-level process supervision**
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## What is this?
|
| 22 |
|
| 23 |
Most interpretability research is **post-hoc** — you find out *why* a model was wrong *after* it's already wrong. **ThinkWhileThinking** flips this:
|
|
|
|
| 18 |
|
| 19 |
> **Real-time reasoning failure detection in small language models via step-level process supervision**
|
| 20 |
|
| 21 |
+
|
| 22 |
+
* 🎥📝 **Demo Video & Technical Write-up:** [Watch the Demo & Read the Architecture on X](https://x.com/krishna__pahuja/status/2066275233028591925?s=46)
|
| 23 |
+
|
| 24 |
+
|
| 25 |
## What is this?
|
| 26 |
|
| 27 |
Most interpretability research is **post-hoc** — you find out *why* a model was wrong *after* it's already wrong. **ThinkWhileThinking** flips this:
|