All tags
Topic: "memory"
not much happened today
gpt-4.1 o3 o4-mini grok-3 grok-3-mini o1 tpuv7 gb200 openai x-ai google nvidia samsung memory model-release hardware-accelerators fp8 hbm inference ai-conferences agent-collaboration robotics model-comparison performance power-consumption sama
OpenAI teased a Memory update in ChatGPT with limited technical details. Evidence suggests upcoming releases of o3 and o4-mini models, alongside a press leak about GPT-4.1. X.ai launched the Grok 3 and Grok 3 mini APIs, confirmed as o1 level models. Discussions compared Google's TPUv7 with Nvidia's GB200, highlighting TPUv7's specs like 4,614 TFLOP/s FP8 performance, 192 GB HBM, and 1.2 Tbps ICI bandwidth. TPUv7 may have pivoted from training to inference chip use. Key AI events include Google Cloud Next 2025 and Samsung's Gemini-powered Ballie robot. The community is invited to participate in the AI Engineer World's Fair 2025 and the 2025 State of AI Engineering survey.
LLMs-as-Juries
gpt-4 gpt-3.5 sdxl ponyxl openai cohere financial-times memory training-data model-usage-limits data-cleansing ai-voice-assistants interface-agents image-generation model-extensions multi-agent-systems
OpenAI has rolled out the memory feature to all ChatGPT Plus users and partnered with the Financial Times to license content for AI training. Discussions on OpenAI's profitability arise due to paid training data licensing and potential GPT-4 usage limit reductions. Users report issues with ChatGPT's data cleansing after the memory update. Tutorials and projects include building AI voice assistants and interface agents powered by LLMs. In Stable Diffusion, users seek realistic SDXL models comparable to PonyXL, and new extensions like Hi-diffusion and Virtuoso Nodes v1.1 enhance ComfyUI with advanced image generation and Photoshop-like features. Cohere finds that multiple agents outperform single agents in LLM judging tasks, highlighting advances in multi-agent systems.