3bc00ca222
LLMs as constraint solvers. Fine-tuning adds constraints to an existing solution. Gentle = small steps near the current solution. Coherent = new constraints consistent with existing ones. Diversity is a COHERENCE mechanism — forces the solver to satisfy all constraints simultaneously. Over-training = one constraint dominating = solver drops competing constraints. Predictions for training behavior grounded in this framework. |
||
|---|---|---|
| .. | ||
| v0 | ||
| apollo-paper-analysis.md | ||
| context-frozen-training.md | ||
| gdn-gradient-flow.md | ||
| gradient-flow-frozen-context.md | ||
| hogwild-convergence.md | ||
| OPEN-QUESTIONS.md | ||
| practical-intuitions.md | ||
| steering-vectors-bridge.md | ||
| SUMMARY.md | ||
| task-vectors-model-merging.md | ||