←back to thread

3 points yalogin | 1 comments | | HN request time: 0.205s | source

OpenAI, Anthropomorphic and every company is putting a lot into training. How is the functionality pipeline filled out for LLMs? What is missing in today’s LLMs that they need to plan for? Just trying to get some insights into the planning process and also what the community sees as the northstar for LLMs without saying AGI
1. kacklekackle ◴[] No.45058525[source]
Right now I get timed out on my thinking queries use of VM in 60 seconds and as a result the responses are less than adequate as it tries to take shortcuts to stay within the time out limit. I can imagine that in the future maybe there won't be a time out limit which would greatly increase the quality of the responses. And more recently the model seems to get stuck reaffirming facts that we already established and moved on from. For some reason it feels it wants to remind me. Additionally, we may have moved on, but then it applies the fact to what we have moved on to so the context needs to be improved.