We may need to be more forceful in the language telling it to wait. Use of ALL CAPS may work. Or repeating the instruction again at the end… "Remember, WAIT until I say Go! before taking any action." No time to test it right now, but you get the idea
LLMS
-
AI Technology Limitations and Expected Improvements in 2023
By
–
That is a limitation of the AI tech right now. The best way around it right now is prompting it to continue. Annoying, I know. But as the technology evolves — probably this year even — the number on a lot of those limits may be raised.
-
Programming with Natural Language While Others Ask Simple Questions
By
–
It's true, most people are asking single sentence questions still. Meanwhile I'm basically programming using natural language. What a world
-
Two Essential Details to Enhance ChatGPT Prompt Results
By
–
Adding these two types of details to a ChatPT prompt will take your results from being generic and expected to specific and interesting.
-
Six Types of Information in ChatGPT Mega-Prompts
By
–
After tons of research and experimentation, here are the 6 types of information I provide in my ChatGPT mega-prompts:
-
Chatbots Lack Causal Reasoning and Agency: Solutions Needed
By
–
Existing chatbots are not causal reasoners. They lack agency. They treat their actions (what they said) as observations and not as interventions. Question: how do we fix this? @yudapearl I think there’s a few solutions, but I’d love to hear you thoughts. @eliasbareinboim
-
Tokenization inequality in AI models and pricing implications
By
–
Ostras qué mal. La tokenización es la forma en la que modelos como GPT-3 subdividen el texto para analizarlo. Y el número de token también es la unidad base por la que OpenAI te cobra: más tokens, más coste Pues esto introduce una desigualdad muy bestia para ciertos lenguajes…
-
Version 0.0.64 Release: Enhanced Robustness for Large Context
By
–
v0.0.64 a bunch of updates making it more robust to large context Updated API chain – @fpingham Updated SQL chain – @fpingham New multistep SQL chain
Parsing of agent responses – h/t @krrish_dh and Wikipedia source information – @rubensmau
