I also use LLMs for stupid shell commands that are not as intuitive as they should be. This also cuts down on looking up the man page or searching Stack Overflow.
PROMPT ENGINEERING
-
How to generate Midjourney AI images
By
–
This image is not real. It's AI generated. Here's how you can generate images like these with Midjourney:
-
Instructor-XL Model Shows Unusual Wikipedia Question Retrieval Prompt
By
–
Hah that one is so weird… https://
huggingface.co/hkunlp/instruc
tor-xl
… "Represent the Wikipedia question for retrieving supporting documents:" -
Treating AI Chatbots Like People for Better Results
By
–
Working with AI is already weird and is going to get weirder. Many forces are combining to make working with AI more like working with people, for better or for worse. In fact, you basically need to treat chatbots like people to get them to work well.
-
Prompt Optimization Techniques Dramatically Impact AI Performance
By
–
Put the information you want the AI to comment into the prompt FIRST and only then ask the question. The performance differences you get from non-obvious differences in prompting approaches are quite large, but it is really hard to know what works well in advance.
-
Improving documentation and examples for function calling and JSON mode
By
–
Thanks everyone for the super valuable inputs! We’ll improve docs and add more examples for function calling and JSON mode. Please keep the feedback coming!
-
Where to Find AI Model Output Token Limits Documentation
By
–
Do you know where they document their output token limit? I can't find that for any of their models
-
Text extraction challenges with token output limitations
By
–
The HTML thing was really just an illustrative example – the general challenge is that there are plenty of text extraction tasks where the output is > 8196 tokens so the more output tokens we can have the easier these things are to put into practice
-
LLM Continuation Trick: Requesting More Output Within Context
By
–
An interesting trick that does work is you can send a prompt requesting "more" and have the LLM pick up again where it stopped That requires round-tripping the work it has done so far, but with a long enough context window (and a will to spend the money) that's quite feasible
-
LLM Output Token Limits: GPT-4, Claude 3, Gemini Pro
By
–
What are the LLMs with the most output tokens these days? GPT-4 and Claude 3 are both 4096. Gemini Pro 1.5 is 8192 This really matters for structured data extraction: even with 1m of input tokens you can't scrape a big webpage into a CSV file if you run out of output tokens