What we learned from a year of building with LLMs. A great read for anyone interested in building things with large language models. → https://
oreilly.com/radar/what-we-
learned-from-a-year-of-building-with-llms-part-i/
… https://
oreilly.com/radar/what-we-
learned-from-a-year-of-building-with-llms-part-i/
…
PROMPT ENGINEERING
-
Lessons Learned Building with Large Language Models
By
–
-
Using Codestral to Implement Code Changes Efficiently
By
–
Prompt codestral to make those changes in the code and it should be able to that.
-
AI Generates Full Applications from Single Natural Language Prompts
By
–
It generates the python code to create a full-fledged application just from a single prompt.
-
RAG Retrieval Optimization Through Representation Engineering and Adapters
By
–
took a while to groq but great clear explanation here! an analogy could be that this is @voooooogel style rep eng applied to rag retrieval queries instead of inference outputs? adapters for everything. you could maybe even do adapters for multimodal data! as chameleon style
-
LLM Tips and Tutorials from Shubham Saboo
By
–
If you find this useful, RT to share it with your friends.
— Shubham Saboo (@Saboo_Shubham_) 31 mai 2024
Don't forget to follow me @Saboo_Shubham_ for more such LLMs tips and tutorials.https://t.co/Cl1nEdpvMsIf you find this useful, RT to share it with your friends. Don't forget to follow me @Saboo_Shubham_ for more such LLMs tips and tutorials.
-
AI Model Troubleshooting Without Product Specifications Works Well
By
–
Even without true RAG, it’s pretty darn good. Usually have to prompt 2-3 times and send more details, but also my use cases were pretty easy. What I thought was interesting was that in every use, I did NOT mention the product brand or model number. I just said “fix this thing”
-
Tool Use Advances: Streaming, Forced Choice, and Multimodal Vision
By
–
Tool use also supports message streaming, "forced" tool choice, and vision support—helping you build more natural, focused, and multimodal experiences.
-
Evaluating Multi-Agent Generative AI Systems: The Fact-Checking Challenge
By
–
A barrier to faster progress in generative AI is evaluations (evals), particularly of custom AI applications that generate free-form text. Let’s say you have a multi-agent research system that includes a researcher agent and a writer agent. Would adding a fact-checking agent
-
Using LLMs to draft professional job follow-up emails
By
–
Follow-up email: Prompt: "I recently interviewed for a remote position as [Job Title] with [Company Name]. Can you help me draft a follow-up email that reinforces my interest in the position and highlights my relevant skills in [Your Skills]?"
-
Using LLMs to Compose Professional LinkedIn Networking Messages
By
–
Networking: Prompt: "I want to expand my network with professionals working remotely in the [Industry]. Could you help me compose a LinkedIn message to connect with them effectively?"