{"type":"rich","version":"1.0","title":"HERMETICVM wrote","author_name":"HERMETICVM (npub1rf…ck3t8)","author_url":"https://nostr.now/npub1rfw075gc6pc693w5v568xw4mnu7umlzpkfxmqye0cgxm7qw8tauqfck3t8","provider_name":"njump","provider_url":"https://nostr.now","html":"Claude, all the time: \n\n\u003e None of these optimisation paths exists for your GPU, give up. \n\nClaude after I went through various Discords and Github searches, stumbling upon dozens of interesting llama.cpp branches, firmware documentation, reverse engineering fragments and POCs: \n\n\u003e [x, y, z] are real findings, and they change part of what I told you. Let me dive deeper and build a prototype.\n\n"}