PREVIEW : Google is preparing Gemini 3.1 Flash Image Preview for the upcoming release. Nano Banana 2 (Flash) model was tested in December based on the Gemini 3 Flash, but it was postponed. Soon?
GENERATIVE AI
-
LFM2-24B-A2B: Liquid AI’s Fastest 24B MoE Model Released
By
–
Meet LFM2-24B-A2B, @liquidai's largest model. 24B MoE, 2B active. Blazing fast even on CPU. Available now in LM Studio 👾💧 lmstudio.ai/models/lfm2-24b-…
→ View original post on X — @maximelabonne, 2026-02-24 15:44 UTC
-
Liquid AI releases LFM2-24B-A2B model for on-device inference
By
–
ollama run lfm2:24b-a2b .@liquidai's latest on-device model is here! It's the largest LFM2 model yet, and is designed to run fast on device, and fits on devices with 32GB of unified memory. Liquid AI (@liquidai) Today, we release our largest LFM2 model: LFM2-24B-A2B 🐘 > 24B total parameters > 2.3B active per token > Built on our hybrid, hardware-aware LFM2 architecture It combines LFM2’s fast, memory-efficient design with a Mixture of Experts setup, so only 2.3B parameters activate each run. The result: best-in-class efficiency, fast edge inference, and predictable log-linear scaling all in a 32GB, 2B-active MoE footprint. 🧵 — https://nitter.net/liquidai/status/2026301771539202269#m
→ View original post on X — @maximelabonne, 2026-02-24 14:36 UTC
-
Liquid AI Releases Largest LFM2-24B-A2B Model with Fast Inference
By
–
Early checkpoint of our biggest LFM2 model to date 🎉 It shows good scaling and extremely fast inference vs. gpt-oss-20b and Qwen3-30B-A3B We'll release an LFM2.5 version with more pre-training and RL in a few months Liquid AI (@liquidai) Today, we release our largest LFM2 model: LFM2-24B-A2B 🐘 > 24B total parameters > 2.3B active per token > Built on our hybrid, hardware-aware LFM2 architecture It combines LFM2’s fast, memory-efficient design with a Mixture of Experts setup, so only 2.3B parameters activate each run. The result: best-in-class efficiency, fast edge inference, and predictable log-linear scaling all in a 32GB, 2B-active MoE footprint. 🧵 — https://nitter.net/liquidai/status/2026301771539202269#m
→ View original post on X — @maximelabonne, 2026-02-24 14:31 UTC
-
Claude AI Now Available Inside PowerPoint for Pro Users
By
–
Claude is now inside PowerPoint. It builds slides from your template.
Edits decks without breaking formatting.
Creates native charts and diagrams you can actually edit.
This is how AI should work — inside your workflow. Available to Pro, Max, Team and Enterprise plan -
Three Common Mistakes When Using Claude AI
By
–
LES 3 ERREURS QUI VOUS TRAHISSENT Erreur 1 : Utiliser Claude sans personnalisation
Prompt générique → Résultat générique Erreur 2 : Accepter la première version
Claude améliore souvent trop. Demandez-lui de se retenir. Erreur 3 : Ne pas relire après correction
Même avec les -
Using Prompt Engineering to Match Personal Writing Style in Claude
By
–
7/ Le prompt "Style Personnel" Pour que Claude écrive vraiment comme TOI :
"Tu vas adopter mon style d'écriture personnel. Analyse d'abord ces 3 exemples de mes textes précédents : [Exemple 1] [Exemple 2] [Exemple 3] Identifie : → Longueur moyenne de mes phrases → Mots et -
Invisible Corrector Prompt for LLMs
By
–
4/ Le prompt "Correcteur Invisible" Quand tu veux juste corriger sans changer le style : "Tu es un correcteur fantôme qui répare les fautes sans laisser de traces de son passage.
Règles strictes : Corrige UNIQUEMENT les fautes objectives (orthographe, grammaire, conjugaison) -
Targeted Improvement Prompting Technique
By
–
5/ Le prompt "Amélioration Ciblée" Quand tu sais exactement ce qui cloche : "Améliore ce texte uniquement sur ces aspects : [Coche ce qui t'intéresse :] Clarté : rends les idées plus limpides sans changer le ton Concision : élimine les mots inutiles tout en gardant
-
Prompt template for humanizing robotic AI-generated text
By
–
3/ Le prompt "Réécriture Intelligente" Pour quand ton texte est trop formel ou robotique :
"Tu es un expert en transformation de contenu qui rend les textes froids et académiques en contenus vivants et engageants. Réécris ce texte en : Humanisant le ton :→ Remplace le jargon