I wonder how much of these changes are pushed by the local LLM shift we've seen recently. I would've expected them to totally focus on GPT-4 updates, but it's nice that we're getting 3.5 improvements.
It's pretty clear that there's a large demand for much cheaper, if weaker LLMs. I'll need to test the "more reliable steerability via the system message" feature, but GPT-3.5's largely monotonic tone and lack of response to the system message was one of its largest weaknesses imo. I'm all for ggml and LLaMa, but there's almost zero need for me to invest in hardware/expensive GPUs (or /hour options) if 3.5 is this cheap. Only downsides I can see are data privacy and OpenAI's "safety" restrictions.
Function calls seem amazing, too. No need to use tokens commanding GPT about its ability to do function calls. I need to test it out though.
Especially given they picked just about the most verbose way of doing it, second only to XML. While this is to be tested, given the examples they give, I somehow doubt that minified description with single-letter function names will perform as well as human-readable (verbose) schemas.
It's pretty clear that there's a large demand for much cheaper, if weaker LLMs. I'll need to test the "more reliable steerability via the system message" feature, but GPT-3.5's largely monotonic tone and lack of response to the system message was one of its largest weaknesses imo. I'm all for ggml and LLaMa, but there's almost zero need for me to invest in hardware/expensive GPUs (or /hour options) if 3.5 is this cheap. Only downsides I can see are data privacy and OpenAI's "safety" restrictions.
Function calls seem amazing, too. No need to use tokens commanding GPT about its ability to do function calls. I need to test it out though.