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

not much happened today

…post provides a comparative analysis of vector databases for Retrieval-Augmented Generation (RAG) systems, highlighting that HNSW is suitable for systems with up to 10M vectors. For larger datasets, Turbopuffer is recommended due to its…

AI News · 2025-12-08
AI News—2025-12-08
Emergency Pod: OpenAI's new Functions API, 75% Price Drop, 4x Context Length (w/ Alex Volkov, Simon Willison, Riley Goodside, Joshua Lochner, Stefania Druga, Eric Elliott, Mayo Oshin et al)

…tension that I feel, you know, I'm sort of halfway between the retrieval augmented generation world, which is kind of like V1 of whatever people I've been building with lms, and then V2 of it has been the agent world. [00:53:09] I feel this…

Podcast · Riley Goodside, Latent.Space, Simon Willison, Alex Volkov · 2023-06-14
PodcastRiley Goodside, Latent.Space, Simon Willison, Alex Volkov2023-06-14
Grok-1 in Bio

…and ethical considerations. Advancements in Language Models and Retrieval Systems: The AI community eagerly discusses the integration of RAG (Retriever Augmented Generation) systems for enhanced model outputs and the unveiling of LLaMa…

AI News · 2024-03-19
AI News—2024-03-19
Gemini 2.5 Pro (06-05) launched at AI Engineer World's Fair

…context window threshold, Claude dynamically switches to a new retrieval-augmented generation (RAG) mode, allowing efficient retrieval across these expanded datasets and supporting large, complex documents such as semiconductor datasheets…

AI News · 2025-06-05
AI News—2025-06-05
Building the Foundation Model Ops Platform — with Raza Habib of Humanloop

…Yeah, chat PDF doing super well. Once RAG started working, like retrieval augmented generation, there was that. But since then, as people are more problem driven. And they're like trying to say, okay, how can we use this? We see a much…

Podcast · Raza Habib, Latent.Space · 2023-09-29
PodcastRaza Habib, Latent.Space2023-09-29
12/20/2023: Project Obsidian - Multimodal Mistral 7B from Nous

…data, model hallucinations, practical application of RAG (Retrieval-Augmented Generation), and the limitations of GPT-4. Notable contributors were @euclaise, @tokenbender, @gabriel_syme, @giftedgummybee. In general, wide-ranging discussions…

AI News · 2023-12-21
AI News—2023-12-21
MiniMax M2 230BA10B — 8% of Claude Sonnet's price, ~2x faster, new SOTA open model

…obstacles because it functions as a direct upgrade to RAGs (Retrieval-Augmented Generation). Another member noted that AI-generated summaries, used for data storage, are often of lower quality than the source material, also raising concerns…

AI News · 2025-10-27
AI News—2025-10-27
Presenting the AI Engineer World's Fair — with Sam Schillace, Deputy CTO of Microsoft

…we have nine tracks. So we have multimodality. We have retrieval augmented generation. Featuring LLM frameworks and vector databases, evals and LLM ops, open source models, code gen and dev tools, GPUs and inference, AI agent applications, …

Podcast · Latent.Space · 2024-03-29
PodcastLatent.Space2024-03-29
Summer of Code AI: $1.6b raised, 1 usable product

…SQLDatabaseChain Vector Stores SQL Record Manager RAG (Retrieval Augmented Generation) Knowledge Graphs SQLDatabaseChain + PGVector for Hybrid Search: A user described their current setup for storing and querying data: using PostgreSQL with…

AI News · 2024-08-30
AI News—2024-08-30
OpenAI completes Microsoft + For-profit restructuring + announces 2028 AI Researcher timeline + Platform / AI cloud product direction + next $1T of compute

…agentic Navigator Mode and a pull request from MCPI to add RAG (Retrieval Augmented Generation) capabilities. A member noted that a GitHub Copilot subscription ($10/month) can be used infinitely with RAG, along with infinite GPT-5 mini,…

AI News · 2025-10-28
AI News—2025-10-28
OpenAI beats Anthropic to releasing Speculative Decoding

…at the LlamaIndex hackathon, demonstrating the capabilities of Retrieval-Augmented Generation in enhancing mechanical workflows. Explore its implementation here and its claimed 6000% efficiency improvement. This project aims to streamline…

AI News · 2024-11-05
AI News—2024-11-05
Bartz v. Anthropic PBC — "Training use is Fair Use"

…agents. Discussion centers on whether Vibe Planning employs Retrieval-Augmented Generation (RAG) or other context-gathering/indexing strategies, and if it integrates web tools to supply updated or just-in-time information for more effective…

AI News · 2025-06-24
AI News—2025-06-24
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

Free. Unsubscribe any time.