Communication is all you need Wrote a blog on how communication is the hardest part of building agents. From this axiom, a bunch of fun hot takes can be derived: Why prompt engineering isn’t going away
Why you need an agent framework
Why we made LangSmith the most user
CODE
-
Communication Foundation: Why Agents Need Better Frameworks
By
–
-
Local OpenAI Swarm Agents with Ollama Integration
By
–
100% Local OpenAI Swarm Agents! OpenAI Swarm is an educational framework that explores ergonomic, lightweight multi-agent orchestration. It's fairly easy to integrate with locally running LLMs through Ollama.
______
Find me → @akshay_pachaar And stay tuned for more on -
Agents as Finite State Machines: LangGraph Framework
By
–
"agents" as finite state machines! if you like this… then you'll like langgraph 🙂
-
New Computer Vision Model Released: Getting Started with New Framework
By
–
x.infer So, a new computer vision model just dropped last night. It's called GPT-54o-mini-vision-pro-max-xxxl. It's a super cool model, open-source, open-weights, open-data, all the good stuff. You're excited. You want to try it out. But it's written in a new framework,
-
GitHub repository for computer use out of the box
By
–
github: https://
github.com/showlab/comput
er_use_ootb
… -
Dictionary Learning Evaluations for Transformer Circuits
By
–
We also shared a variety of new evaluations we're experimenting with in our dictionary learning work (
https://
transformer-circuits.pub/2024/august-up
date/index.html#interp-evals
…), along with a case study of our experiences using those evals (
https://
transformer-circuits.pub/2024/august-up
date/index.html#evals-case-study
…). -
Sparse Autoencoders Resolution Enhancement Through Data Oversampling
By
–
Relatedly, increasing the amount of sparse autoencoder data related to a particular topic can be used to increase the resolution of features related to that topic. https://
transformer-circuits.pub/2024/september
-update/index.html#oversampling
… -
Decomposing Successor Heads Using Independent Component Analysis
By
–
We replicated Gould et al.'s “successor heads” paper, and found that independent component analysis can further decompose these heads into a "successor" component, induction component, and category components. https://
transformer-circuits.pub/2024/september
-update/index.html#successor-heads
… -
Crosscoders as Model Comparison Tools: Experimental Interpretability Approach
By
–
One neat thing is that, very experimentally, crosscoders can be used to "diff" models: comparing between, say, a pretrained model and a fine-tuned one, to see how they differ at a more basic level.