Content
@
0 reply
0 recast
0 reaction
Greg
@greg
I haven't been following the AI space very closely, especially outside of OpenAI stuff. How far behind are open source alternatives? I've heard about stuff like llama2 supposedly being decent for chat but I'm assuming the agents/function calling and whatnot is a different story?
7 replies
1 recast
13 reactions
m_j_r
@m-j-r.eth
none of it is really production-level. then again, GPT-4-Turbo's 128k context is no surprise, given Yarn-Mistral has tenuous parity already. really a question of capital cost, since there's a wide variety of performance boosts that can get folded into one model within a stack like Autogen + MemGPT + Voyager.
1 reply
0 recast
1 reaction
m_j_r
@m-j-r.eth
there's a "open-source is 6 months behind" but tbqh everything, including GPT-4-Turbo, is a few months away from a complete suite of bleeding-edge technique. I'd also question the cost, since juggling many smaller models can outweigh performance of the singular juggernaut.
0 reply
0 recast
0 reaction
