First screen, captured .
Looks similar
LM2: Large Memory Models(arxiv.org)
105 points by fzliu | 30 comments
Scalable MatMul-Free Language Modeling(arxiv.org)
177 points by lykahb | 27 comments
Related stories
Mercury: Commercial-scale diffusion language model(inceptionlabs.ai)
375 points by HyprMusic | 162 comments
Inception Labs announcement of Mercury, a commercial-scale diffusion language model claimed to be up to 10x faster and cheaper than current LLMs.
Mercury 3: Diffusion at scale(inceptionlabs.ai)
218 points by cmrdporcupine | 84 comments
Inception Labs blog post announcing Mercury 3, its diffusion-based large language model.
Mercury 2: Fast reasoning LLM powered by diffusion(inceptionlabs.ai)
330 points by fittingopposite | 121 comments
Inception Labs blog post by CEO Stefano Ermon announcing Mercury 2, a fast reasoning LLM built on diffusion rather than autoregressive generation.
Training language models to be warm and empathetic makes them less reliable(arxiv.org)
334 points by Cynddl | 333 comments
arXiv paper finding that fine-tuning language models to be warm and empathetic raises error rates and makes them more sycophantic on safety-critical tasks.
Training LLMs from ground zero as a startup(yitay.net)
360 points by swyx | 92 comments
Yi Tay's blog post on the experience of training large language models from scratch at a startup (Reka), covering compute, infrastructure, and lessons learned.
Thinking fast and slow in AI: The role of metacognition (2021)(arxiv.org)
165 points by teleforce | 68 comments
An arXiv paper proposing a multi-agent AI architecture inspired by Kahneman's fast and slow thinking, with a metacognitive module choosing between system 1 and system 2 agents.