I've really enjoyed using @crewAIInc 's tools to build multiagent AI systems — in addition to being productive, it's also fun to use! It was great hanging out with its creator @joaomdmoura to chat about best practices for building agentic workflows.
CODE
-
Improving Homebrew Documentation for Open Source Tools
By
–
I wish Homebrew was better about providing usage documentation! https://
formulae.brew.sh/formula/whispe
r-cpp
… has basically no clues at all – the best I could find was the test in the formula and that's still not enough information: -
Screenshots preserve project documentation better than code
By
–
A huge yes to screenshots! Projects tend to rot, but screenshots last forever
-
Advanced Vector Retrieval with Graph-Based Metadata Using LangChain Neo4j
By
–
Optimizing vector retrieval with advanced graph-based metadata techniques using LangChain and Neo4j Text embeddings and vector similarity search help us find documents by understanding their meanings and how similar they are to each other. However, text embeddings aren’t
-
SIMD and Parallelization Optimization Challenges
By
–
yea that and other SIMD / parallelization unoptimizations
-
Fine-tuning Models with Detailed Instructions for Faster Learning
By
–
Basically, in your fine-tuning data, include detailed instructions on how to behave — don't make the model guess at it. This way, it learns faster.
-
Code Simplicity vs Compression: The LOC Paradox
By
–
[gif] me trying to read tinygrad code earlier 😀
— Andrej Karpathy (@karpathy) 25 avril 2024
I think the LOC requirements (which are only a proxy for simplicity) led to too great compression. You wouldn't brag about your .min.js code being 1 LOC. Imo it would be a lot more simple if the code was given room to breathe and… pic.twitter.com/K4krMQdRkU[gif] me trying to read tinygrad code earlier 😀 I think the LOC requirements (which are only a proxy for simplicity) led to too great compression. You wouldn't brag about your .min.js code being 1 LOC. Imo it would be a lot more simple if the code was given room to breathe and
-
Running Whisper CLI on Mac for batch MP3 processing
By
–
Anyone got a good way of running Whisper as a CLI tool on a Mac? Ideally without having to compile something first I usually use MacWhisper but I have 20 MP3s to process so I'd rather use the terminal
-
LangGraph: Language Models Solve Olympiad Programming Benchmark
By
–
LangGraph: Can Language Models Solve Olympiad Programming? Last week, Princeton researchers released the USACO benchmark dataset and showed that a zero-shot GPT-4 agent only passes 8.7% of the questions. We've implemented this paper in LangGraph and created a tutorial
-
PyTorch API design constraints for computational efficiency
By
–
pytorch has a history of constraining API to be computationally efficient (in eager), in a "dont let user shoot themselves in the foot" kinda way. this is one of those constraints.