UX is so underrated for developer tools. The difference between 'I have to use this' and 'I want to use this' is exactly these small touches.
@whats_ai
-
Separate Models for Review: External Eval Pipelines Essential
By
–
Separate model for review is the move. Same blind spots on generation and verification is exactly why I keep pushing for external eval pipelines.
-
Prospective Clinical Study Validates Medical AI Properly
By
–
An actual prospective clinical study, not just a benchmark. This is how medical AI should be validated.
-
O’Reilly Launches 10-Hour LLM Building and Operating Bootcamp
By
–
Big news! We teamed up with @OReillyMedia (the publisher of the very first ML books I ever read back in 2018 ) to launch our brand-new “Building & Operating Large Language Models” 10-hour bootcamp, now live on the O’Reilly learning platform! Put simply: the same practical
-
KIVA Streamlines AI Content Research and Workflow Automation
By
–
Here’s how I research for my daily content and how KIVA can save hours per week 👇
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 28 août 2025
Normally: tabs everywhere → read releases, scan socials, cite-check, outline, publish
With KIVA: one click expands into related web searches, pulls social discussions, SEO ideas, outlines →… pic.twitter.com/ATTeff84yHHere’s how I research for my daily content and how KIVA can save hours per week Normally: tabs everywhere → read releases, scan socials, cite-check, outline, publish With KIVA: one click expands into related web searches, pulls social discussions, SEO ideas, outlines →
-
LLM Evaluations: Highest ROI Strategy for Model Optimization
By
–
If you’re not measuring, you’re guessing. Here’s why LLM evaluations are the highest-ROI move 👇
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 27 août 2025
– Most failures come from bad specs, no real data, or models misapplying rules
– Fix it with custom evaluations: JSON checks, tool errors, schema constraints, LLM-as-judge
– Build… pic.twitter.com/JtEtklqM4PIf you’re not measuring, you’re guessing. Here’s why LLM evaluations are the highest-ROI move – Most failures come from bad specs, no real data, or models misapplying rules – Fix it with custom evaluations: JSON checks, tool errors, schema constraints, LLM-as-judge – Build
-
Startup Onboarding Speed vs Enterprise Bureaucracy Challenges
By
–
That's pretty fast! Must be a startup?! It took me a week in my last job (years ago) to get into the actual code in a big company due to all the logistics, HR stuff, access, etc.
-
Gemini 2.5 Represents Major Leap in AI Creativity and Editing
By
–
This isn’t just another AI drop.
This feels like a real leap in practical AI creativity + editing. Try it and tell me if you agree #AI #GenerativeAI #Gemini25 #NanoBanana -
Google’s Nano Banana Model Now Available Free Gemini App
By
–
Best part: Free in Gemini App & the Google AI Studio @googleaidevs API: just $0.039 per image Not hype. The “Nano Banana” model is now my go-to.
-
Model shows major upgrade despite minor text glitches
By
–
Not perfect (yet): Text glitches (“so goood” ) Sometimes misses tiny factual details But compared to every other model → this is a HUGE upgrade.