ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Ouvir "#77- Ring Attention e janelas de contexto de 1M, o RAG está morto?"
Sinopse do Episódio
Fala galera, nesse episódio eu explico como a gente consegue escalar a janela de contexto de um LLM pra mais de 1 milhão de tokens usando Ring Attention. Além disso eu discuto se a abordagem usando RAG está morta com esses avanços na janela de contexto.
Paper Lost in the Middle: https://arxiv.org/pdf/2307.03172.pdf
Gemini technical report: https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf
Paper Ring Attention: https://arxiv.org/pdf/2310.01889.pdf
Instagram do podcast: https://www.instagram.com/podcast.lifewithai
Linkedin do podcast: https://www.linkedin.com/company/life-with-ai
Paper Lost in the Middle: https://arxiv.org/pdf/2307.03172.pdf
Gemini technical report: https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf
Paper Ring Attention: https://arxiv.org/pdf/2310.01889.pdf
Instagram do podcast: https://www.instagram.com/podcast.lifewithai
Linkedin do podcast: https://www.linkedin.com/company/life-with-ai
Mais episódios do podcast Vida com IA
#140- A corrida dos LLMs.
11/12/2025
#137- Dicas de prompt.
20/11/2025
#136- Reinforcement Learning.
13/11/2025
#134- DeepSeek OCR é bom mesmo??
30/10/2025
#132- História dos LLMs.
16/10/2025
In God we trust