Iterating Towards LLM Reliability with Evaluation Driven Development If you've interacted with the LangChain GitHub repo, you may have noticed a helpful GitHub bot called Dosu You may have also noticed that it's been improving over time! In this blog @devstein64 dives into
AI
-
AI Misinformation Echo Chambers Fuel Societal Polarization
By
–
I already see people dismissing information they don’t like as “AI generated.” AI content will not create echo chambers where people reject things that they don’t believe. But it will clearly supercharge that already dangerous trend; giving even more excuses for not listening.
-
Multi-agent system with orchestrator for flexible error handling
By
–
Great result! This system based on 3 "team member" agents (Web search, Terminal, & Assistant) managed by an Orchestrator. It has no fixed graph structure : at each step the Orchestrator decides which actions should be taken. Advantage: more flexible in case of error!
-

Is Cosine Similarity of Embeddings Really About Similarity?
By
–
Is Cosine-Similarity of Embeddings Really About Similarity? Steck et al.: https://
arxiv.org/abs/2403.05440 #ArtificialIntelligence #DeepLearning #MachineLearning -
Using ChatGPT to process and clean prompt text
By
–
Yup, just feed it first to ChatGPT and ask to ´remove xml tags”, it will make the prompt look normal and you will be able to use it!
-

CodeRabbit: AI-Powered Code Review Solution for Developers
By
–
Introducing CodeRabbit, The Future of AI-Powered Code Reviews! While the LLMs have significantly transformed code generation, the code review process still lags behind and remains stressful! Having efficient and effective code review processes is crucial! That's where
-

Fast RAG Application with Ollama and Nomic Embedding Model
By
–
Crazy FAST RAG with Ollama, Nomic Embedding Model, Groq API Cool attempt by @mesudarshan to create a really really fast RAG application. Utilizes a lot of OSS models and frameworks! YouTube: https://
youtube.com/watch?v=TMaQt8
rN5bE
… GitHub Repo: https://
github.com/sudarshan-koir
ala/rag-chat-with-pdf
… -
GPT-4 Still Preferred by 10% Users in Model Comparison
By
–
Did a thread on this. Around 10% that answered still found GPT-4 better
-

DataRobot Showcases AI Platform at Gartner Data Analytics Summit
By
–
Who’s at @Gartner_inc Data & Analytics Summit this week? Stop by our booth #1440 to meet with #appliedAI experts and see the DataRobot AI Platform in action. See you there! https://
bit.ly/42PVZTX #GartnerDA
