Search Latent Space

Results for “retrieval augmented generation”

Articles, conversations, profiles, and grounded writeups.

?
Search tips

Keyword matches words; semantic matches meaning and exact titles or names; hybrid combines both. In keyword mode, use quotation marks for exact phrases. Author matches published credits. Year applies to posts; wiki entries have no author or publication year. You can also use author:"Ada" or type:podcast in non-regex searches.

Reset filters

Select Apply filters to update results.

445 results

Efficiency is Coming: 3000x Faster, Cheaper, Better AI Inference from Hardware Improvements, Quantization, and Synthetic Data Distillation

…the cognitive abilities that we discussed with LLMs, which is a retrieval augmented generation has large language model. [00:42:59] Nyla Worker: To converse, uh, we have a text to speech, automatic speech recognition. We're working on…

Podcast · Latent.Space · 2024-09-03
PodcastLatent.Space2024-09-03
Sora pushes SOTA

…A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM - NVIDIA/trt-llm-rag-windows Mistral ▷ #deployment (7 messages): Model Mix-Up Alert: @casper_ai noted that thebloke's…

AI News · 2024-02-16
AI News—2024-02-16
not much happened today

…cutting-edge applications with AI Agents, MCPs, and RAG (Retrieval-Augmented Generation) techniques, confirmed by this tweet. The event aims to foster innovation in AI application development using these advanced tools and methodologies.…

AI News · 2025-07-07
AI News—2025-07-07
Stable Diffusion 3 — Rombach & Esser did it again!

…of our upcoming model release, and invite you to ... Corrective Retrieval Augmented Generation — Why RAGs are not enough?!!: Paper || Tweet SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model: Generic image inpainting…

AI News · 2024-03-05
AI News—2024-03-05
OpenAI's gpt-oss 20B and 120B, Claude Opus 4.1, DeepMind Genie 3

…scraped data from forums, Discord, Slack, and websites using retrieval-augmented generation (RAG), combined with workflow automation to streamline communication and processes. Engineer navigates Tech Stack: The AI Engineer is skilled in…

AI News · 2025-08-05
AI News—2025-08-05
AGI is Being Achieved Incrementally (OpenAI DevDay w/ Simon Willison, Alex Volkov, Jim Fan, Raza Habib, Shreya Rajpal, Rahul Ligma, et al)

…it the retriever, which basically does, it does RAG, it does retrieval augmented generation against the content you've uploaded, but Code Interpreter also has access to the files that you've uploaded, and those are both in the same bucket, …

Podcast · Raza Habib, Latent.Space, Rahul Sonwalkar, Simon Willison, Alex Volkov · 2023-11-08
PodcastRaza Habib, Latent.Space, Rahul Sonwalkar, Simon Willison, Alex Volkov2023-11-08
Learnings from o1 AMA

…in this post. This update emphasizes Swiftide's efficiency in Retrieval Augmented Generation applications, enabling faster data ingestion and querying. Leveraging Flux for Efficient Image Generation: An experiment with Flux demonstrated a…

AI News · 2024-09-14
AI News—2024-09-14
not much happened today

…context length is a widespread issue. RAG Ramifications: Retrieval Augmented Generation Revelation: Users discussed whether Kimi employs RAG for handling large documents, noting that other models like Qwen appear more efficient at managing …

AI News · 2025-12-19
AI News—2025-12-19
DeepSeek-V2 beats Mixtral 8x22B with >160 experts at HALF the cost

…labels - microsoft/MS-MARCO-Web-SearchChe cos'è la Retrieval Augmented Generation (RAG)? | Databricks: La RAG (Retrieval Augmented Generation) è un approccio architettonico che utilizza i dati come contesto per i modelli linguistici di…

AI News · 2024-05-06
AI News—2024-05-06
Qwen3-Next-80B-A3B-Base: Towards Ultimate Training & Inference Efficiency

…Kaggle; try it in the Qwen chat app (see @Alibaba_Qwen). Image generation and OCR: ByteDance Seedream 4.0, Florence-2, PaddleOCRv5, Points-Reader Seedream 4.0 (ByteDance): New T2I/Image Edit model merges Seedream 3 and SeedEdit 3 and is…

AI News · 2025-09-11
AI News—2025-09-11
The End of Finetuning — with Jeremy Howard of Fast.ai

…area. So today's zero shot, few shot learning equivalent is retrieval augmented generation, you know, RAC, which is like, just like few shot learning is a thing. Like it's a real thing. It's a useful thing. It's not a thing anybody would…

Podcast · Latent.Space · 2023-10-19
PodcastLatent.Space2023-10-19
Multi-modal, Multi-Aspect, Multi-Form-Factor AI

…the world! 💪 One of the goals we’ve had when starting Rek...Retrieval Augmented Generation Research: 2017-2024: RAG literature review including: REPLUG, Fusion-in-Decoder, KNN-LM, RETRO, FLARE, Knowledge Graph Fusion-in-Decoder, SILO,…

AI News · 2024-04-15
AI News—2024-04-15
Your place in Latent Space

Join Latent Space.

Sign in with Google, or get the newsletter by email.

Loading Google sign-in…

or subscribe by email

Includes all newsletters: Latent Space (2–3 times a week), AI for Science (2–3 times a month), and AINews (every weekday). Free. Unsubscribe any time.