Kyle @darsnack.bsky.social · 11/06/2026Trying to use Siri AI to achieve the impossible. Will report back if AGI is complete. 000
Kyle @darsnack.bsky.social · 12/11/2024I guess the take-away is that frozen LLMs can be heavily quantized down to 2-bits which makes any classic approach (CPU, GPU, ASIC) more competitive in terms of power. 1/ 100