Table of Contents
Week 42 of 2024 (2024-10-14 to 2024-10-20) weekly
Pinboard Activity
Recent URLs
- Accelerate Product Delivery Using Generative AI and Smart Contracts Tickets, Thu, Oct 17, 2024 at 2:00 PM | Eventbrite
- [2410.10934] Agent-as-a-Judge: Evaluate Agents with Agents
- 2024 Events Agenda - Boston Fintech Week
- Mistral releases new AI models optimized for laptops and phones | TechCrunch
- gmpalter/cl-forth: Common Lisp implementation of the Forth 2012 Standard
- Apple Engineers Show How Flimsy AI 'Reasoning' Can Be | WIRED
- System Prompts - Anthropic
- All System Prompts For Anthropic's Claude, Revealed | Hackaday
- openr/reports/OpenR-Wang.pdf at main · openreasoner/openr
- Improve public speaking skills using a generative AI-based virtual assistant with Amazon Bedrock | AWS Machine Learning Blog
- PyTorch Optimizers Aren't Fast Enough. Try These Instead | by Benjamin Bodner | Oct, 2024 | Towards Data Science
- OPEN-RAG: A Novel AI Framework Designed to Enhance Reasoning Capabilities in RAG with Open-Source LLMs - MarkTechPost
- OpenR: An Open-Source AI Framework Enhancing Reasoning in Large Language Models - MarkTechPost
- Create a multimodal chatbot tailored to your unique dataset with Amazon Bedrock FMs | AWS Machine Learning Blog
- OpenAI's Newest Possible Threat: Ex-CTO Murati; Google's Mini-ChatGPT Moment — The Information
- System Prompts - Anthropic
- OpenAI unveils experimental 'Swarm' framework, igniting debate on AI-driven automation | VentureBeat
- Anthropic CEO goes full techno-optimist in 15,000-word paean to AI | TechCrunch
- Tool support · Ollama Blog
- Common Lisp implementation of the Forth 2012 Standard | Hacker News
Summary AI tech
Recent AI and Technology News
- Events and Conferences
- Accelerate Product Delivery event using Generative AI and Smart Contracts (Oct 17, 2024)
- Boston Fintech Week 2024 agenda released
- AI Model Developments
- Mistral releases new AI models optimized for edge devices
- OpenAI unveils experimental 'Swarm' framework for AI-driven automation
- DeepMind introduces Michelangelo benchmark for long-context LLMs
- Research and Frameworks
- Agent-as-a-Judge: New method to evaluate AI agents
- OPEN-RAG: Framework to enhance reasoning in RAG with open-source LLMs
- OpenR: Open-source framework for improving reasoning in large language models
- Industry News
- Apple engineers demonstrate limitations of AI 'reasoning'
- Anthropic releases system prompts for Claude
- Anthropic CEO publishes 15,000-word essay on AI optimism
- Tools and Applications
- AWS introduces AI-based virtual assistant for public speaking improvement
GitHub Activity
Summary github
Recent GitHub Activity Summary
- Watched Repositories
- cl-forth (gmpalter/cl-forth)
- run-llama-locally (anordin95/run-llama-locally)
- swarm (openai/swarm)
- mlflow (mlflow/mlflow)
- ollama-ebook-summary (cognitivetech/ollama-ebook-summary)
- gptel (karthink/gptel)
- graphiti (getzep/graphiti)
- graphiti (graphiti-api/graphiti)
- ollama (ollama/ollama)
- orgzly-android-revived (orgzly-revived/orgzly-android-revived)
- uv (astral-sh/uv)
- Awesome-CloudOps-Automation (unskript/Awesome-CloudOps-Automation)
- clojure (clojure/clojure)
- resyntax (jackfirth/resyntax)
Goodreads Activity
TODO Review Goodreads activity for the week
No Goodreads activity recorded for this week.