Une explication bien faite du fonctionnement interne des LLMs : tokens, embeddings, positional encoding, attention, feed-forward…
https://t.co/Z0aoSOeqiz
Bottega, l'outil d'orchestration d'agents de code de Vincent Daubry, est désormais open source — après 1 000 user stories livrées en production.
https://t.co/V0KpXnSEx4
Tu backend ahora tiene una boca.
Salió open source una plataforma donde tu agente IA se conecta por MCP, encuentra el error y propone el fix mientras tú mirabas el dashboard equivocado.
Esto era tu trabajo hace una semana.
Se llama Maple.
#M5StackNew 🎉LLM-8850 Kit (4G) Released
LLM-8850 Kit is a high-performance AI accelerator kit designed for edge AI and embedded computing scenarios. It consists of the LLM-8850 Card AI accelerator card, which is based on #Axera AX8850 SoC, and the LLM-8850 PiHat adapter board, enabling the @Raspberry_Pi platform to easily integrate high-compute AI acceleration and rapidly build compact, efficient edge intelligence systems. This is 4GB memory version of the LLM-8850 Kit.
✨Features
✅Ultra-compact form factor: M.2 M-Key 2242 size & High-performance NPU: 24 TOPS @ INT8, octa-core Cortex‑A55 1.7 GHz CPU
✅Memory: 4GB 64‑bit LPDDR4x, 4266 Mbps (2+2)
✅Hardware video engine: 8 K @ 30 fps H.264/H.265 encoding, 8 K @ 30 fps decoding, supports 16-channel 1080P parallel decoding
✅Secure boot & encryption: AES / DES / 3DES / SHA‑256 hardware security module
✅Native AXCL: one-click execution of full-stack models including CNN, Transformer, CLIP, Whisper, Llama3.2, Qwen3, InternVL3, etc., supports simultaneous H.264/H.265 encode/decode transcoding
🛒 Get Yours:
Shopify: https://t.co/Ncjp7ElMne
AliExpress: https://t.co/sPuGiQW9AB
#M5Stack #IoT #M5StackNew #RaspberryPi #Axera #EdgeAI #AIAcceleration #LLM #MachineLearning #Hardware #Makers #EmbeddedSystems
해변의 돌멩이를 하나씩 골라 바닥에 놓는다. 색을 맞추고, 위치를 잡고, 또 하나를 고른다. 영국 출신 아티스트 저스틴 베이트먼이 만드는 고양이 모자이크 랜드 아트다.
붙이지 않는다. 굳히지 않는다. 바람이 불면 흩어지고, 파도가 오면 사라진다. 그래서 영상이 남아있다.