Hosein Rastegar
devops724
AI & ML interests
None yet
Recent Activity
reacted
to
MaziyarPanahi's
post
with 🚀
about 11 hours ago
From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output
I ran 6 experiments trying to use Anthropic's SAE steering for JSON generation.
- Base model: 86.8% valid JSON
- Steering only: 24.4%
- Fine-tuned: 96.6%
- FSM constrained: 100%
Steering is for semantics, not syntax.
https://huggingface.co/blog/MaziyarPanahi/sae-steering-json
liked
a model
2 days ago
inference-net/Schematron-8B
liked
a model
2 days ago
inference-net/Schematron-3B
Organizations
None yet