Weekly Digest #153

Articles

Why AutoGPT engineers ditched vector databases

1. AutoGPT’s decision to drop vector databases is a move in the right direction, to focus on delivering value instead of thinking about technology.
2. Coding agents such as GPT Engineer, GPT Pilot, or even GitHub Copilot[6], don’t use vector databases — instead they find relevant context by files recency, proximity in the file system, or looking for references of a given class or function.
3. BabyAGI’s assumptions to store memories in vector dbs remained unchanged, but it seems like there aren’t many updates there and the original author decided to keep the algorithm simple as an example/foundation for other projects.
4. Complexity is the worst enemy of a developer.

AI Report 2023

Stop Obsessing Over Tools

Encrypted traffic interception on Hetzner and Linode targeting the largest Russian XMPP (Jabber) messaging service

Tutorials

How I stay reasonably anonymous online

til, Today I Learned

Tools

Startup-CTO-Handbook, a book covering leadership, management and technical topics for leaders of software engineering

Google Coding Competitions Archive

Off-topic

Visualizing MBTA Data

20 ways to visualise percentage