AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Industrial AI Podcast
Newsflash: Pierer invests Millions in Hochreiter‘s XLSTM
Feb 5, 2024
Sepp Hochreiter, a researcher in LLM alternative architecture, discusses the advancement of XLSTM, the significance of context length in language models, the exploration of XLSTM potential and IP rights in Europe, and the evaluation of methods and abstract reasoning. The potential applications of large language models for companies are also explored.
31:46
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- XLSTM offers advantages over transformer models in terms of accuracy, power consumption, and abstract reasoning, making it ideal for complex tasks like coding and logic.
- The founders of NXI have invested a significant amount of money in training XLSTM models using over 1000 GPUs and plan to explore revenue streams such as licensing the technology and developing their own products.
Deep dives
Founding of NXI and Focus on XLSTM
In this podcast episode, Professor Dr. Dezapur Hader and Albert discuss the founding of their company NXI, which aims to advance the XLSTM idea. XLSTM is a linear approach to language models that seeks to outperform transformer models in terms of speed and efficiency. The company has secured funding to test and compare XLSTM with existing language models, focusing on scaling laws and smaller vs. larger models. The ultimate goal is to develop a large language model based on XLSTM that can be brought to the market.
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode