5/ In just under two weeks, bounty hunter Ansh created a bot that summarizes every Ribbon PR, and replies with a Ribbon Award. The bot makes it seamless for Ribbon customers to implement Ribbon Awards in their PRsand their development workflow.
AGENTS
-
Ribbon Awards: Decentralized Accomplishment Platform Leverages AI
By
–
2/ @RibbonAward is a rewards platform founded by @arshamg_ . Users earn Ribbon Awards as decentralized proof of accomplishments. Arsham had a few ideas to implement AI, but instead of stretching his team thin, Arsham chose to delegate and assign the task on Replit Bounties.
-
GitHub Actions Bot Integrates AI PR Analysis with Ribbon Awards
By
–
4/ The idea he posted? Create a bot to integrate Github Actions with Ribbon. This would enable Ribbon customers to award their developers based on their recent PR. AI would then analyze PRs and generate a Ribbon award.
-
Evaluating Language Model Values: Frameworks for Global AI Alignment
By
–
Our preliminary findings show the need for rigorous evaluation frameworks to uncover whose values language models represent. We encourage using this methodology to assess interventions to align models with global, diverse perspectives. Paper:
-
Language Models Show Western-Centric Opinions and Steerability
By
–
We develop a method to test global opinions represented in language models. We find the opinions represented by the models are most similar to those of the participants in USA, Canada, and some European countries. We also show the responses are steerable in separate experiments. pic.twitter.com/QzHmRPNqSl
— Anthropic (@AnthropicAI) 29 juin 2023We develop a method to test global opinions represented in language models. We find the opinions represented by the models are most similar to those of the participants in USA, Canada, and some European countries. We also show the responses are steerable in separate experiments.
-
AutoGPT: Self-Iterating AI Agents with GPT-3.5 and GPT-4
By
–
AutoGPT combines GPT-3.5 and GPT-4 via API, allowing projects to be created that have been iterating on their own prompts and reviewing each iteration to improve and build upon it. AutoGPT: Everything You Need To Know – KDnuggets https://
bit.ly/43Z1f7X -
Newark schools test AI tutoring bot for student learning
By
–
Officials in Newark, New Jersey, are testing an AI enabled tutoring bot in three schools
-
AI Chatbots Fall Short in Real-World Shopping Tasks
By
–
I Asked #AI #Chatbots to Help Me Shop. They All Failed https://
bit.ly/3P0qYIa via @WIRED -
Securing AI Agents: Data Permissioning and Leak Prevention
By
–
We want to build AI agents that use internal data to create external interfaces (i.e. customer service bots). How should we be thinking about permissioning? How do we prevent agents from leaking internal data sources via prompt engineering or simply a mistake? @strandbrown