“🤯 MIND-BLOWING: Meta’s SINGLE new data center = ALL US data centers in 2005! 🏭 💡 1.5 nuclear plants just to power it ⚡️ Data centers consume nations’ worth of power. Quantum chips rewrite computing’s rules. This isn’t coincidence. It’s convergence.
https://x.com/baierSF/status/1866374250380284137
AI at Meta on X: “New release from Meta FAIR — Meta Motivo is a first-of-its-kind behavioral foundation model for controlling virtual physics-based humanoid agents for a wide range of complex whole-body tasks. The model is capable of expressing human-like behaviors and achieves performance https://t.co/yGUu5JzGlW” / X – https://x.com/AIatMeta/status/1867664693319586289
“META JUST KILLED TOKENIZATION !!! A few hours ago they released “Byte Latent Transformer”. A tokenizer free architecture that dynamically encodes Bytes into Patches and achieves better inference efficiency and robustness! (I was just talking about how we need dynamic
https://x.com/scaling01/status/1867573707247346003
“Training LLMs to Reason in a Continuous Latent Space Meta presents Coconut (Chain of Continuous Thought), a novel paradigm that enables LLMs to reason in continuous latent space rather than natural language. Coconut takes the last hidden state of the LLM as the reasoning state
https://x.com/omarsar0/status/1866518791733342563
“Surprise #NeurIPS2024 drop for y’all: phi-4 available open weights and with amazing results!!! Tl;dr: phi-4 is in Llama 3.3-70B category (win some lose some) with 5x fewer parameters, and notably outperforms on pure reasoning like GPQA (56%) and MATH (80%).
https://x.com/SebastienBubeck/status/1867379311067512876
Byte Latent Transformer: Patches Scale Better Than Tokens | Research – AI at Meta
https://ai.meta.com/research/publications/byte-latent-transformer-patches-scale-better-than-tokens/
“@cover_thz Meta dropped Llama 3.3, a 70B open model with similar performance to Llama 3.1 405B, but significantly cheaper It’s text only for now. Available to download at Meta’s Llama page and on HuggingFace
https://x.com/adcock_brett/status/1865804416667770992
Meta quietly leans on rival GPT-4 despite Zuckerberg’s bold Llama claims | InfoWorld
https://www.infoworld.com/article/3617048/meta-quietly-leans-on-rival-gpt-4-despite-zuckerbergs-bold-llama-claims.html
“As we continue to explore new post-training techniques, today we’re releasing Llama 3.3 — a new open source model that delivers leading performance and quality across text-based use cases such as synthetic data generation at a fraction of the inference cost.
https://x.com/AIatMeta/status/1865079067390956006
For Llama updates please see the Open Source category
