Search Latent Space

Results for “retrieval augmented generation”

Articles, conversations, profiles, and grounded writeups.

Reset filters
About search and filters

Keyword matches words; semantic matches meaning; 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 your search.

445 results

not much happened today

…leaderboard to select suitable embedding models for their Retrieval Augmented Generation (RAG) applications. It explains the difference between Bi-Encoder and Cross-Encoder models, how embedding models are benchmarked, and how to select a…

AI News · 2024-08-17
AI News—2024-08-17
OpenRouter's State of AI - An Empirical 100 Trillion Token Study

…plus a GitHub repo and pip install smallevals. It builds golden retrieval eval datasets without depending on the generation model, and includes a local dashboard to inspect rank distributions, failing chunks, and dataset stats, enabling…

AI News · 2025-12-04
AI News—2025-12-04
CodeLLama 70B beats GPT4 on HumanEval

…Summary RAG Demystified: In response to @aiguruprasath's query, Retrieval Augmented Generation (RAG) was explained by @darthgustav. as AI with the capability to directly access knowledge for searching data or semantic matching, enhancing…

AI News · 2024-01-30
AI News—2024-01-30
not much happened today

…accuracy) before proceeding. They also recommend considering Retrieval-Augmented Generation (RAG) for organization-specific tasks, which may not require full model training. Leasing hardware or using cloud services for testing is advised to…

AI News · 2026-01-08
AI News—2026-01-08
Poolside gets $12B reverse-execuhire to NVIDIA; founders stay for $1B, employees go for $6B, Infraco scaling to 7GW neocloud

…historical/location identification, or airgapped knowledge retrieval. Commenters generally frame this as an intentional or acceptable specialization tradeoff: Qwen 3.x may be shifting toward coding/agentic use where external retrieval is…

AI News · 2026-08-21
AI News—2026-08-21
The world's first fully autonomous AI Engineer

…text, sensory readings, robot actions. [48,605 impressions] Retrieval Augmented Generation (RAG) and Tools Retrieval Augmented Thoughts (RAT) shows that iteratively revising a chain of thoughts with information retrieval can significantly…

AI News · 2024-03-12
AI News—2024-03-12
not much happened today

…with factual recall expected to be supplied via domain data or retrieval. Multiple replies stress that small models like Gemma 3 270M should be fine-tuned on task-specific datasets (e.g., title generation, tagging, sorting). In this regime,…

AI News · 2025-08-22
AI News—2025-08-22
AI for Engineers — Sign up for private Beta

…year. The course content is: GPT API Basics Prompt Tooling and Retrieval Augmented GenerationCode Generation with GPT Image Generation with Dall-E, Stability, Lexica, and Midjourney Speech-to-Text with Whisper Finetuning & Running Open…

Article · Latent.Space · 2023-05-19
ArticleLatent.Space2023-05-19
GPT4o August + 100% Structured Outputs for All (GPT4o August edition)

…cloud and core engineering teams. AI Development and Tools RAG (Retrieval-Augmented Generation): Discussions on the importance of RAG for integrating human input and enhancing AI systems' capabilities. JamAI Base: A new platform for…

AI News · 2024-08-07
AI News—2024-08-07
Grok 4 Fast: Xai's distilled, 40% more token efficient, 2m context, 344 tok/s frontier model

…citation verification, and confidence thresholds (see Retrieval‑Augmented Generation: https://arxiv.org/abs/2005.11401). This trades breadth for precision and would benefit from per‑source trust scores and coverage fallback policies.…

AI News · 2025-09-19
AI News—2025-09-19
[AIE Summit Preview #1] Swyx on Software 3.0 and the Rise of the AI Engineer

…AI Engineering Stack System of reasoning: Foundation model APIs Retrieval augmented generation (RAG) stack: Connects models to data AI UX: New modalities and interfaces beyond chatbots • Building Products with Foundation Models Replicating …

Podcast · Latent.Space · 2023-10-07
PodcastLatent.Space2023-10-07
Too Cheap To Meter: AI prices cut 50-70% in last 30 days

…new members are welcomed. Links mentioned: Getting Started with Retrieval-Augmented Generation: Part 1 of the LLM University module on Retrieval-Augmented Generation.Retrieval Augmented Generation (RAG) - Cohere Docs: Retrieval Augmented…

AI News · 2024-08-09
AI News—2024-08-09
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.