Iterate Relentlessly
Prompt → inspect → refine. Every “bad” answer is feedback! Tighten scope, add detail, or rephrase until it works for you.
@whats_ai
-
Iterate Relentlessly: Refine Prompts Through Feedback
By
–
-
Prompt Engineering Best Practices for Advanced Reasoning Models
By
–
Provide Context Upfront
Newer reasoning models (e.g., OpenAI o-series) reward rich briefs: include schemas, constraints, desired format. It does not need info on "how to perform the task".
One well-structured prompt with all the details it needs > 10 back-and-forth tweaks. -
Role-Based Prompting: Instantly Transform AI Response Tone
By
–
Set the Stage with Roles
“You are a physics teacher…” vs. “You are a stand-up comedian…” Changes tone, depth, and framing instantly. -
Chain-of-Thought Prompting: Enhance AI Reasoning Step-by-Step
By
–
Force it to “Think”: Chain-of-Thought
Add “Let’s solve this step by step.”
Great for math, logic, or multi-part reasoning where the model tends to rush.
Or use a reasoning model if you budget/time allows for it! -
Gemini-Embedding-001 Tops MTEB Leaderboard with Cost-Effective Batch Mode
By
–
🚀 Gemini-Embedding-001 is live
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 15 juillet 2025
• Tops the MTEB leaderboard, ahead of OpenAI & Cohere
• Batch mode = 2× cheaper for large-scale RAG
• Pre-compute & cache embeddings for faster retrieval
• Text + code only (no image/audio… yet)
Pure value or oversold? Drop your verdict 👇… pic.twitter.com/RVhwuUhG00Gemini-Embedding-001 is live • Tops the MTEB leaderboard, ahead of OpenAI & Cohere
• Batch mode = 2× cheaper for large-scale RAG
• Pre-compute & cache embeddings for faster retrieval
• Text + code only (no image/audio… yet) Pure value or oversold? Drop your verdict -
Grok 4 Launches: 2x Better Than Claude Opus 4
By
–
🚀 Grok 4 just dropped
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 15 juillet 2025
• 2× better than Claude Opus 4 on ARC-AGI-2
• Multi-agent Heavy tier: $300 / mo
• Elon: “smarter than any grad student”
Hype or game-changer?👇#Grok4 #xAI #AInews #AGI pic.twitter.com/u00uuFHvwwGrok 4 just dropped • 2× better than Claude Opus 4 on ARC-AGI-2
• Multi-agent Heavy tier: $300 / mo
• Elon: “smarter than any grad student” Hype or game-changer? #Grok4 #xAI #AInews #AGI -
Fine-Tuning and RLHF: Complete LLM Developer Training Course
By
–
Super excited to release our final 2-hour session of our "10-hour transition course" from developer to LLM developer! Lesson 6 is LIVE: Fine-Tuning, LoRA, RLHF & Everything You Need to Re-train Your LLMs If you’ve already nailed prompting and retrieval in the first two free
-
ChatGPT Prompt Engineering: 7 Actionable Tricks to Boost AI Results
By
–
New video! ChatGPT Hacks: 7 Tricks to Instantly Boost Your AI Results Struggling to get nice, reliable answers from ChatGPT or other LLMs? Here's a 15-minute video that walks through the seven most actionable prompt engineering moves you can start using today:
-
Build a Local AI Coding Agent Guide
By
–
Let's do it! https://
open.substack.com/pub/louisbouch
ard/p/build-a-local-ai-coding-agent?r=25qlky&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
… -
Local LLM Agent System with Tool Chaining and Extensibility
By
–
It will:
– Use Ollama to run a local LLM (we’ll use qwen3:32b)
– Handle tool calls for reading/writing files, listing directories, and running shell commands
– Chain multiple tools to solve multi-step tasks
– Be easily extendable with things like web search or formatters