Week in Review #0000

Prompt: “autonomous agents”

2023–04–17 => 2023–04-21

I’m trying to create a post per week to summaryze what I learned during the week, papers I read, news I found interesting, code I experimented and/or contributed to:

• Google Brain and DeepMind merged: it seems an answer to OpenAI and other independent AI labs, to consolidate an unique front for AI research on Google. Pretty curious about what’s coming next, given that Google and DeepMind never stopped releasing really important pieces that paved the way to current AI hype (e.g. Transformer, LLMs, etc).
• Started exploring LangChain: I really like how they are organizing LLMs into Agents and external APIs as Tools, so we can chain them together to create LLM-based pipelines. They are really fast in incorporating new concepts (like Autonomous Agents), making it easier to explore most recent LLM pieces through only one API.
• Started exploring Autonomous Agents: AutoGPT, BabyAGI, JARVIS, Generative Agents are getting great momentum: “Recursive” agents that start with one goal and keep exploring and increasing sub-tasks to reach the goal. When used together with tools like LangChain, can make pretty powerful tools.
• Stability jumped on the LLM train by releasing its first LLM model.
• It seems LLM models size and data must grow together (https://arxiv.org/abs/2203.15556). Which means that scaling data is possibly the next step for LLM.
• HuggingGPT (or JARVIS) was released and it’s pretty impressive: an LLM that can search and use ML models hosted on Hugging Spaces to solve tasks. It would be nice to have it integrated in LangChain.
• Elon wants to sue MS and another of his rockets exploded, the launchpad seems OK, it only has a giant crater bellow it ;-)
• Learnt about https://memprompt.com/