Does anyone have a link to a chatbot demo I can try out right now that's serving a model that has been fine-tuned to add additional targetted knowledge (not behavior – actual information that it can answer questions about) to that model?
PROMPT ENGINEERING
-
Severe Prompt Injection Pattern Identified
By
–
I think this might be a pretty severe prompt injection pattern
-
ML NLP LLMs RAG Tips and Tutorials Newsletter
By
–
If you’re interested in:
– ML/NLP
– LLMs
– RAG Connect with me → @Saboo_Shubham_ My Newsletter → https://
unwindai.substack.com Everyday, I share tip & tutorials on above topics on X and my newsletter. -
ML NLP LLMs RAG Newsletter Tips and Tutorials
By
–
Thanks for sharing Min! If you’re interested in:
– ML/NLP
– LLMs
– RAG Connect with me → @Saboo_Shubham_ My Newsletter → https://
unwindai.substack.com Everyday, I share tip & tutorials on above topics on X and my newsletter. -
Llama 3 Prompt Documentation Sets Standard for Model Templates
By
–
That's legit the hardest part about getting any model to work at the moment – those prompt templates are so inconsistently documented The Llama 3 prompt docs are genuinely great – very clear, unambiguous – I just wish every other model had docs like that
-
Managing Special Tokens in AI Models: Guidance Gaps
By
–
Has anyone seen published guidance about how to avoid tokens (including special things like [INST] or ) messing things up, for any of the available models? I've not seen good documentation on this myself yet
-
LangSmith Achieves 30% Accuracy Improvement Without Prompt Engineering
By
–
How Dosu used LangSmith to achieve a 30% accuracy improvement with no prompt engineering One of the goals of LangSmith is to help teams set up a data flywheel. By capturing LLM outputs alongside user feedback, we can help developers automatically use that feedback to improve
-
Mistral Large and Mixtral 8x22B Performance on GSM1K Dataset
By
–
Nice paper. Very good performance by Mistral Large and Mixtral 8x22B on the new GSM1K dataset! Results from Table D (plotted in Figure below) are also a good reminder that models are very sensitive to prompt. In general, it is also good to use sampling & majority voting to
-
Newsletter for AI prompts, tools, and workflows for entrepreneurs
By
–
If you think this is helpful, you might want to sign up for my newsletter. Every week, I send out: – Ideas for AI prompts
– Information about AI tools
– Tips on workflows Join over 7,500 entrepreneurs for free: https://
godofprompt.ai/subscribe -
Productivity: 10 hours of work in 2 hours with ChatGPT
By
–
Copy and paste these ChatGPT productivity prompts to get 10 hours of work done in 2: