Post
1,176
Unlocking hidden skills inside Google's model
https://dejan.ai/blog/latent-skills/
AI models hold skills that no prompt can unlock. A NeurIPS 2025 study trained small numbers of randomly chosen weights in Llama and Qwen models of four sizes, across ten tasks: 10 to 100 trained weights closed up to half the gap between the original model and a fully fine-tuned one. We repeated the test on Google's smallest Gemma model, Gemma 3 270M. The best of 20 prompt wordings got it to sort five numbers correctly 1% of the time. After we trained 1,000 of its 100 million weights (0.001%), it sorted correctly 97% of the time. The same method switched on reversing word lists (84%) and clean JSON output (99% with 30 weights), and lifted long addition, while multiplication stayed near 30% even with 100,000 trained weights.
https://dejan.ai/blog/latent-skills/
AI models hold skills that no prompt can unlock. A NeurIPS 2025 study trained small numbers of randomly chosen weights in Llama and Qwen models of four sizes, across ten tasks: 10 to 100 trained weights closed up to half the gap between the original model and a fully fine-tuned one. We repeated the test on Google's smallest Gemma model, Gemma 3 270M. The best of 20 prompt wordings got it to sort five numbers correctly 1% of the time. After we trained 1,000 of its 100 million weights (0.001%), it sorted correctly 97% of the time. The same method switched on reversing word lists (84%) and clean JSON output (99% with 30 weights), and lifted long addition, while multiplication stayed near 30% even with 100,000 trained weights.