|
|
|
|
|
by JohnBooty
8 days ago
|
|
At a 50-100x speedup even a GPT-4o class model could perhaps compete with much newer models simply by thinking deeper, doing harness-controlled Ralph loops, etc. Sure, then it might be "only" ~2-5x faster, but, you wouldn't need to throw all the ASICs into the trash bin. One could also imagine hybrid models, where part of the model is burned into ASICs and part of the model exists in VRAM/HBM2 so it can be updated. I don't have enough low-level knowledge to evaluate the technical or economic feasibility of the above ideas, however. |
|
Sometimes you need speed; sometimes you need quality. There are very different use cases for each. For my own workflows, I sometimes want something very simple done ASAP; other workflows need "subjective" reasoning and careful crafting of responses.