Turns out this has been an open issue on GitHub for Mastodon core for five years now https://
github.com/mastodon/masto
don/issues/2668
… Not sure if any of the many alternative implementations have it yet
OPEN SOURCE
-
Five-Year GitHub Issue in Mastodon Core Remains Unresolved
By
–
-
Running Your Own Instance Without Vendor Lock-in
By
–
No idea I'm afraid! That's why I chose to run my own instance, I didn't want to have to pick one (though apparently you can move between them without losing your profile, which is reassuring)
-
Building Tools Responsibly: Ethics of Dual-Use Technology
By
–
I've built tools (like Django) that can be used for truly evil things, and I hate that If Mastodon had been explicitly designed to support evil behaviour I would reject it This particular case feels more to me like rejecting email software because that can be used for evil too
-
Lightweight Python SQLite alternatives to Rails PostgreSQL Redis stack
By
–
Yeah the main project is surprisingly heavy: Rails and PostgreSQL and Redis and Sidekiq – there's a lot of state involved! But there are some promising alternatives that are more lightweight – this one is just Python and SQLite for example https://
github.com/tsileo/microbl
og.pub
… -
Paying for Mastodon self-hosting as alternative infrastructure choice
By
–
That's one of the reasons I'm paying $9/month for my Mastodon hosting provider – I see it as similar to running your own email server or website hosting
-
Mastodon Decentralized Server Model Easier Cheaper Healthier Community
By
–
… which is SO MUCH easier and cheaper if you are running a server with only a few hundred active users Mastodon has been around for 6 years at this point and from dipping in over the past few days seems to be the opposite of a toxic environment – they're doing something right!
-
Langchain Python Package Implements Advanced LLM Prompting Techniques
By
–
@hwchase17
's Python package Langchain implements and lets you easily compose many published LLM prompting techniques. Implements self-asking, web search, REPL math, and several of my own prompts. -
Cohere Launches Sandbox Open-Source Packages for LLM Development
By
–
We are excited to announce Sandbox, a set of experimental open-source packages on GitHub that give you the tooling, functions, demos, and libraries you need to get started with large language models (LLMs) fast! Dive in https://
txt.cohere.ai/introducing-sa
ndbox-coheres-experimental-open-source-initiative/
… -
Topically: LLM-powered topic modeling tool suite launched
By
–
Topically is out! Launch it https://
github.com/cohere-ai/sand
box-topically
… Topically: A suite of tools that help you use the best of topic modeling to make sense of text collections (messages, articles, emails, news headlines, etc.) using large language models. -
Toy Semantic Search: Simple AI-powered search engine with embeddings
By
–
Toy Semantic Search is out! Fork it https://
github.com/cohere-ai/sand
box-toy-semantic-search
… Toy Semantic Search: A simple semantic search engine built with the Cohere API. The search algorithm here is fairly straightforward, using embeddings to find the paragraph that matches the question's representation.