I've also gotten really good at it. I think people who dislike it must have given up too early. You have to learn what to expect, what works, what doesn't work, how to position your cursor (e.g. to not get distracting suggestions), and how to prompt it well via code/comments
PROMPT ENGINEERING
-
LMSYS Performance Reflects RLHF Choices, Not General Capabilities
By
–
perhaps bc lmsys performance is less a judgment on general capabilities than it is of rlhf choices i dug into the data a little for curiosity sake – always worth remembering how short (and single turn) most of these queries are.
-
Tokenization Security Risks in AI Input Processing
By
–
I'm never 100% sure if that works or not – did that input get turned into those single tokens (arguably an injection security risk) or did it tokenize the input as "<" and then "gh" and so on?
-
Special tokens in AI: delimiters and use cases explained
By
–
Special tokens like these are used to delimit things like "this section is the user asking a question" vs "this section is an answer from the LLM" – or sometimes for things like "this is the output of a separate tool" I have no idea what those gh ones are for!
-
Instruction Hierarchy Advances LLM Robustness Against Prompt Injections
By
–
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details:
-
Hidden Reasoning in AI Interfaces Through Tag Parsing
By
–
If you control the interface, you can even have it reason within tags and then parse them out so the user doesn’t see.
-
Chain of Thought in Foreign Languages for AI Reasoning
By
–
This idea of having the AI do Chain of Thought in foreign languages & tell you the results in English so as not to ruin the surprise of the game is fascinating.
-
Understanding AI Models Through Conversation and Testing
By
–
I usually just start by saying “hi” to the model, and go from there. It takes time to really understand how well a model works.
-
Running Meta-Llama-3-8B-Instruct with LLM CLI Tool
By
–
Yes, you can run prompts like this: llm -m Meta-Llama-3-8B-Instruct -o temp 0.1 "3 names for a pet rhino" https://
github.com/simonw/llm-gpt
4all?tab=readme-ov-file#model-options
… -
Claude Hack: Grammar Structure Works for All LLMs
By
–
Yes! For sure try it with Claude, it's essentially a Hack for all LLMs, are it's dealing with grammar and how to structure sentences on a general level, which all LLMs will understand.