ORRA

🚨 Breaking News - OPENAI vient d’ÉTEINDRE la CONCURRENCE avec un NOUVEAU MODÈLE !! OpenAI vient d'annoncer GPT-4o, qui est 2x plus rapide que GPT-4 Turbo et il est GRATUIT ! Ses performances de traitement de la voix, des images, des vidéos et du texte ont été BOOSTÉES ! 🚀

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n

This is how you can make changes to the edits.

Vous vous rendez compte qu’on voit la barrière à l’entrée de certainement LE truc le plus difficile à apprendre en informatique, la modélisation et l’animation 3D, tomber sous nos yeux ? Époque de fou. Je viens de commander une imprimante 3D parce que, pour la première fois, je me dis que je peux m’y mettre et découvrir (alors qu’avant, je n’ai jamais eu le temps d’apprendre à la main). Maintenant, avec l’IA, tout va plus vite. Tout devient accessible. On peut découvrir tellement de choses qui étaient inaccessible avant. Est ce que c’est bien ou mal ? Tel est la question.

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.

We've redesigned Claude Code on desktop. You can now run multiple Claude sessions side by side from one window, with a new sidebar to manage them all.

Just launched a SeedDance 2.0 value ranking site. Higgsfield is currently #1 for cost efficiency: ~¥25 ($3.5 USD) per minute of video. The former #1 & #2 are from past promos and unavailable. Higgsfield's current deal is the best active offer worth grabbing. Check the full ranking: mirobiz.com/lab/wangzha-ra… #SeedDance #AIvideo #CostAnalysis #Higgsfield

Introducing Higgsfield Marketing Studio powered by Seedance 2.0: a single workflow from product to finished ad. Bring a product image or paste a product link, use an avatar from your photo or build one inside the tool, and generate your ad end-to-end in 9 ad styles - UGC, unboxing, reviews, and more. New users get up to 70% off, with up to 14 days of Unlimited generations.* Start here: higgsfield.ai

Here’s a Midjourney V7 style reference you might want to explore: --sref 3348769398 This style is European comic caricature with cinematic lighting. It blends Franco-Belgian bande dessinée energy with a more modern, slightly painterly digital finish. Feels like a quirky European animated movie full of personality.

Now this is an ad.

Seedance 2.0 - Advanced Workflow Series 6. Rough to Final Animation Use basic sketches and provide character and environment references to Seedance to receive a full-color final animation or render. Workflow + Prompts 👇

Seedance 2 is out globally on Freepik! 🎸 And now you got to learn how to prompt for it. So I went ahead and made a Spaces workflow for you - link below. And here's a prompt for you to kick off: [STYLE] Ultra-high detail Pixar-quality cinematic animation, 8K, soft global illumination, individual hair and fur strands, realistic fabric simulation, shallow depth of field, warm cozy lighting [FORMAT] 16:9, cinematic multi-shot scene, slow tension build [SCENE] Cozy bedroom at night with strong 80s personality, colorful retro posters on walls, desk with glowing computer, warm lamp. [CHARACTERS] A young man with short dense curly blonde hair forming soft rounded clumps, pale skin, slightly tired blue eyes, wearing a black hoodie A golden retriever with thick light golden fur and expressive eyes. [CAMERA SYSTEM] Smooth cinematic camera, slow push-ins, medium and close shots, no jitter. A scene showing the guy coding. The dog wakes up from some noise. the guy asks what's up. the dog walk to across the room to a closed closet door. noise coming from inside. the guy walks up and gets ready to open the door and calms the dog.

Ton Mac va pouvoir faire tourner un des meilleurs modèles open source au monde. Par Google. En local. Sans abo 🆓. Sans internet. Y'a jamais eu autant de puissance dispo en open source. Google vient de sortir Gemma 4 en open source (Apache 2.0). Ce que ça change : Aujourd'hui tu paies Cursor, Claude, ChatGPT.. tous les mois pour coder avec l'IA. Même les trucs simples : renommer une variable, générer un composant basique, répondre à une question sur ton code. Avec un modèle comme Gemma 4 en local : >tu gardes ton abo principal pour les tâches complexes (debug, archi, gros refacto) >tu fall back sur le modèle local pour tout le reste : autocomplete, questions simples, petits agents qui tournent en boucle (on parlait de ça en @smoltalk ce matin) >tes agents autonomes qui font 200 appels API par jour ? Ils tournent en local, gratos >il peut lire ~200 fichiers de code d'un coup sans perdre le fil (256K tokens de contexte) >c'est Google, pas un modèle chinois où t'as aucune idée de ce qui se passe avec tes données Résultat : classé #6 mondial, et ça tourne sur un Mac 16GB. ⚠️ Ça remplace pas Opus ou Codex pour les trucs les plus complexes. Mais pour les 70% de tâches simples que tu fais chaque jour : c'est gratuit, offline, et ça tourne sur ton ordi. Ps : le petit modèle (E2B) tourne même dans un navigateur (oui, dans un onglet Chrome)

🚨 Les développeurs d’Anthropic ne rédigent plus de code ? Le CEO Amodei dévoile la boucle de code qui consiste à concevoir la prochaine version de Claude, en grande partie générée par Claude lui-même.

This is going, where we all dreaded AI might go. Not just predicting will you click an ad but what will you react, seeing a post or ad or anything else. Powerful and next-level move by Meta!

Claude + Arcads is too powerful...

this is terrifying. Claude Opus 4.6 + Remotion can now generate videos. It can do motion design, demos and animations from a single prompt... it's so over.

Cette nouvelle est GIGANTESQUE Google avait déjà inventé les Transformers (le T de ChatGPT) qui ont révolutionné l’IA. Ils présentent maintenant TurboQuant : un algorithme de compression qui a le potentiel de diviser par dix les besoins de mémoire des datacenters IA…

Seedance 2.0 photorealistic macro cinematic Shot Video Prompt used 👇 FORMAT: 15s / 6 SHOTS / single continuous chase energy / no dialogue STYLE: Macro jungle floor, towering grass blades, dew drops, damp earth vs neon pink cyber-implants, photorealistic macro cinematic Shot 01 (0:00-0:02) Dive from the canopy of a giant fern down to a cybernetically enhanced rhinoceros beetle sprinting across a fallen, moss-covered log. Shot 02 (0:02-0:04) Camera tracks parallel to the beetle's mechanical legs, sweeps under its glowing pink thorax, and snaps to the spinning micro-rotors on its back. Shot 03 (0:04-0:07) A heavy rain droplet dislodges a pebble from above; the beetle initiates a thruster-assisted sidestep, scraping its metallic horn against a fungal stalk. Shot 04 (0:07-0:10) The path dives into a dense thicket of thorny briars, spiderwebs, and overlapping leaves; the camera seamlessly navigates the micro-labyrinth. Shot 05 (0:10-0:13) The beetle bursts from the thicket into a clearing, a splash of muddy dew hitting the lens as its optical sensors flash tactical warnings. Shot 06 (0:13-0:15) Camera pulls back exponentially, transitioning from the micro scale to reveal an immense, sprawling bioluminescent greenhouse, the beetle lost in the glowing flora.