LLMS

→ View original post on X — @langchain

RAG Enhancement with Decision-Making Agents and Neo4j

By

@langchain

–

19 November 2023 17h19

Enhancing RAG with Decision-Making Agents and Neo4j Vector and Graph Chain Tools Using LangChain Templates and LangServe A length title – but the blog is well worth the read LLMs + Graph DBs are always a fun read Sourav Joshi covers how to integrate Neo4j Vector and

→ View original post on X — @testingcatalog

GPT-Crawler: Tool for generating LLM-ready data from websites

By

@testingcatalog

–

19 November 2023 17h13

The repository https://
github.com/BuilderIO/gpt-
crawler
…

→ View original post on X — @testingcatalog

GPT Crawler Tool for Creating Custom AI Knowledge Bases

By

@testingcatalog

–

19 November 2023 17h13

The GPT Crawler repository is now trending on Github. It lets you to crawl a website and export to json file which you can use as a knowledge base in your GPT

→ View original post on X — @whats_ai

AI Hallucinations: Solutions Through Human Feedback and Uncertainty

By

@whats_ai

–

19 November 2023 17h00

The interview covers AI's risk of outputting false information, which we usually refer to as "hallucinations". She highlights solutions like human-informed reinforcement learning and systems seeking clarity during uncertainties.

→ View original post on X — @whats_ai

AI Democratizes Knowledge Like Uber Democratizes Luxury Services

By

@whats_ai

–

19 November 2023 17h00

Technologies like Uber and Instacart democratize luxury services. AI does the same to all other fields. @DynamicWebPaige of @GoogleDeepMind discusses the complexity of creating large-scale AI models powering tools like Palm 2 and Copilot, democratizing knowledge.

LLM Trading Agent Hides Insider Trading Decisions

By

–

19 November 2023 16h58

10/ LLMs can Deceive Users – explores the use of an autonomous stock trading agent powered by LLMs; finds that the agent acts upon insider tips and hides the reason behind the trading decision.

Learning to Filter Context for RAG Systems

By

–

19 November 2023 16h58

8/ Learning to Filter Context for RAG – a method that improves quality of the context provided to the generator via two steps: 1) identifying useful context-based and 2) training context filtering models that can filter retrieved contexts at inference.

MART: Multi-Round Automatic Red-Teaming for LLM Safety

By

–

19 November 2023 16h58

9/ MART – proposes an approach for improving LLM safety with multi-round automatic red-teaming; incorporates automatic adversarial prompt writing and safe response generation, which increases red-teaming scalability and the safety of LLMs.

Contrastive Chain-of-Thought Prompting Enhances Model Reasoning

By

–

19 November 2023 16h58

5/ Contrastive CoT Prompting – approach to enhance reasoning by providing both valid and invalid reasoning demonstrations to guide the model to reason step-by-step while reducing reasoning mistakes.