The decisions you need to make… – how much context you provide
– where/what/how you summarize
– how you break up knowledge
– etc. …are a constant balance of context length, model speed and cost, use case, latency, keeping up w latest tools, and more.
PROMPT ENGINEERING
-
Balancing Context Length, Speed, and Cost in AI Systems
By
–
-
GPT Calls as Thoughts: Building Agents with Reflection and Memory
By
–
1 GPT call is a bit like 1 thought. Stringing them together in loops creates agents that can perceive, think, and act, their goals defined in English in prompts. For feedback / learning, one path is to have a "reflect" phase that evaluates outcomes, saves rollouts to memory,
-
AI System Generates Wisdom From Input Data
By
–
Turns out if you insert food into that guy, he spits back wisdom!
-
AutoGPTs: The Next Frontier of Prompt Engineering and AI Systems
By
–
Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run(). https://t.co/EKy84pa5bB
— Andrej Karpathy (@karpathy) 2 avril 2023Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run().
-
Agent AI Corrects Generated Programs Using Test Feedback
By
–
By patching you mean how the agent corrects the generated program? We get the feedback from the tests and feed it back to LLM, to make an intelligent decision on what needs to get fixed.
-
Fine-tuned LLMs vs General Models: When Customization Matters
By
–
Yeah, the need for customized find-tuned LLMs decreases when the general LLM can do what you need out of the box. The only use I see for fine-tuned LLMs is when GPT-4 doesn’t want to do what you need, and prompt engineering doesn’t help.
-
Accessing GPT-4 ChatGPT Subscription Automation Selenium
By
–
But you can access gpt-4 in ChatGPT if you have the subscription. And then automate the access via selenium plugin.
-
LLM Agents Execute Computer Tasks Through Recursive Self-Improvement
By
–
7/ LLMs for Computer Tasks – shows that a pre-trained LLM agent can execute computer tasks using a simple prompting scheme where the agent recursively criticizes and improves its outputs.
-
Building an iOS App Without Prior Knowledge Using AI Tools
By
–
I don't know iOS development. Yet, I built a usable iOS app yesterday and it took me only a few hours. I learnt a lot about how to prompt well to make AI based tools not only write the code as you want but also make them debug for you! AI
-
Framework Development with Programmatic Prompt Engineering Focus
By
–
100%. At this point, I’m focused on getting the framework working, then will improve on the task creation through some sort of programmatic prompt engineering ideas I have.