zlacker

[return to "Memory and new controls for ChatGPT"]
1. drcode+s8[view] [source] 2024-02-13 18:51:56
>>Josely+(OP)
This kind of just sounds like junk that will clog up the context window

I'll have try it out though to know for sure

◧◩
2. Prosam+S8[view] [source] 2024-02-13 18:54:33
>>drcode+s8
I've been finding with these large context windows that context window length is no longer the bottleneck for me — the LLM will start to hallucinate / fail to find the stuff I want from the text long before I hit the context window limit.
◧◩◪
3. drcode+B9[view] [source] 2024-02-13 18:58:14
>>Prosam+S8
Yeah, there is basically a soft limit now where it just is less effective as the context gets larger
[go to top]