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

Claude Opus 4.5: 3rd new SOTA coding model in past week, 1/3 the price of Opus

…QA accuracy, reduce hallucinations, and improve text-to-SQL generation and RAG retrieval. Christmas Code Drop Sparks Causal Reasoning: A member shared a Causal Reasoning Module for interpretable AI, implementing causal discovery,…

AI News · 2025-11-24
AI News—2025-11-24
1/4/2024: Jeff Bezos backs Perplexity's $520m Series B.

…maintaining access controls. @absolutt1 suggested that the Retrieval Augmented Generation (RAG) system would be a good fit. Gradio 4.13 Lands with a Bang: @abidlabs announced the Gradio 4.13 release, detailing the new features. He also…

AI News · 2024-01-05
AI News—2024-01-05
Qwen-Image: SOTA text rendering + 4o-imagegen-level Editing Open Weights MMDiT

…website with a clean UI, models, a memory system and free RAG (Retrieval-Augmented Generation) for all tiers, using OpenRouter as the main AI generation backend. PyrenzAI app faces speed and security critiques: A user critiqued the newly…

AI News · 2025-08-04
AI News—2025-08-04
Latent Space Chats: NLW (Four Wars, GPT5), Josh Albrecht/Ali Rohde (TNAI), Dylan Patel/Semianalysis (Groq), Milind Naphade (Nvidia GTC), Personal AI (ft. Harrison Chase — LangFriend/LangMem)

…an intense hatred for RAG. [01:50:11] Dylan Patel: Right, like retrieval augmented generation is, is, is like the most like, I just have an intense like innate hatred for it. Wait, wait, you retweeted me [01:50:18] swyx + Josh Albrecht:…

Podcast · Latent.Space · 2024-04-06
PodcastLatent.Space2024-04-06
MetaVoice & RIP Bard

…Catch @seldo's discussion about language models and retrieval-augmented generation (RAG) for enterprises today. More details on the talk can be found here. Self-RAG Evolution in Retrieval Dynamics: The Self-RAG method by @AkariAsai allows a…

AI News · 2024-02-07
AI News—2024-02-07
not much happened today

…how NotebookLM works, particularly its use of RAG (Retrieval-Augmented Generation), and was trying to use it for unrelated content in a single source, which requires a custom solution. NotebookLM Set for Gemini 2.5 Pro Upgrade?: Members are…

AI News · 2025-06-03
AI News—2025-06-03
DeepMind SIMA: one AI, 9 games, 600 tasks, vision+language ONLY

…new video spotlights Command-R, demonstrating its capacity for Retrieval Augmented Generation (RAG) and integration with external APIs, detailed in Lets RAG with Command-R. Introducing Devin, AI in Software Engineering: The world's alleged …

AI News · 2024-03-14
AI News—2024-03-14
not much happened today

…underwriting automation. Gemini File Search API enables agentic retrieval augmented generation (RAG) with MCP server integration. Together AI and Collinear launch TraitMix for persona-driven agent simulations integrated with Together Evals.…

AI News · 2025-11-11
AI News—2025-11-11
Top 5 Research Trends + OpenAI Sora, Google Gemini, Groq Math (Jan-Feb 2024 Audio Recap) + Latent Space Anniversary with Lindy.ai, RWKV, Pixee, Julius.ai, Listener Q&A!

…different paradigm for, for text generation, reasoning, plan generation if we can get diffusion to work. [00:23:51] swyx: For text. And then the second one is Dowie Aquila's contextual AI, which is working on retrieval augmented language…

Podcast · Latent.Space · 2024-03-09
PodcastLatent.Space2024-03-09
Adept Fuyu-Heavy: Multimodal model for Agents

…a project by @zain_hoda, is gaining attention for its use of Retrieval Augmented Generation (RAG) to improve SQL query generation, capable of indexing DDL/table schemas and text. The project has generated buzz on social media. LlamaIndex…

AI News · 2024-01-25
AI News—2024-01-25
Alibaba Yunqi: 7 models released in 4 days (Qwen3-Max, Qwen3-Omni, Qwen3-VL) and $52B roadmap

…and third‑party teams integrated Grok fast models (@ssankar). Retrieval, context engineering, and agent research MetaEmbed (Flexible Late Interaction): Append learnable “meta tokens” and only store/use those for late interaction, enabling…

AI News · 2025-09-23
AI News—2025-09-23
Common Corpus: 2T Open Tokens with Provenance

…extended runs. RAG for Long-term Memory: Inquiry about RAG (Retrieval-Augmented Generation) was made, along with requests for user experiences and guidance on using it for long-term data retention. A user recommended Dify as a simple…

AI News · 2024-11-14
AI News—2024-11-14
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.