caught myself writing out my thoughts like an LLM :/
LLMS
-

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
-
LLMs Writing Better FastHTML Code Through Documentation Improvements
By
–
Yes lots. Spent a long time testing how well models could write idiomatic FastHTML whilst tweaking each part of the docs. Generally when LLMs did poorly, it turned out our docs for humans needed improvement too! 🙂
-
AI Model Restrictions and Security Policy Violations
By
–
Quoi ? Non, c'est pas IA j'étais vraiment là ce jour là avec une bière à la main Blague à part, ces restrictions sont assez lourdes, je suis d’accord : une fois sur deux, il dit que ça viole sa politique de sécurité.
-
Gemini 2.5 Flash Image Launch and Major AI Company Updates
By
–
AI NEWS: The mysterious 'nano-banana' model is officially here — as Gemini 2.5 Flash Image. Plus, more news from OpenAI, Alibaba, AI2, and Anthropic. Here's everything you need to know:
-

Google Nano-Banana Ranks High on LM Arena for Image Editing
By
–
Sans surprise, sur LM ARENA, Nano-Banana, le dernier modèle de Google pour éditer et faire des images… est très haut.
-
Fine-tuning frameworks for notebooks without quality loss
By
–
For sure, we have notebooks with different fine-tuning frameworks here. No quality loss either!
-

xAI Launches Grok Code Fast Model on Poe Platform
By
–
New on Poe: Grok Code Fast! This high-performance, cost-efficient model from xAI is optimized for agentic coding applications. It offers visible reasoning traces, strong steerability, and supports a 256k context window. (1/2)
-
Strong Instruction Following Capabilities in AI Systems
By
–
Instruction following is strong with this one.
-

Google Nano Banana Model Launch Announcement
By
–
Have you tried it yet? http://
replicate.com/google/nano-ba
nana
…
