Emerging social platforms: A new era of digital interaction

As the world continues to evolve and seek alternatives to social media giants like Facebook, Instagram, and Twitter, a wave of innovative platforms are emerging that aim to redefine our online experiences. These new-age networks present an opportunity for users to break free from the constraints of pre-defined algorithms while enjoying greater control over their digital identities.

Beyond decentralization: The promise of innovation

One core feature shared by these emerging platforms is their decentralized nature. By distributing power across multiple nodes rather than concentrating it in one central authority, they create an environment less susceptible to censorship and manipulation. This not only fosters freedom of expression but also inspires innovation as developers can build on top of existing frameworks or even create entirely new ecosystems.

- Farcaster: a decentralized platform whose model encourages developers to contribute features tailored specifically for its user base. As more developers join the network and bring unique perspectives into the mix, Farcaster has the potential to become increasingly diverse in functionality – giving users access to a wide range of tools without being locked into any single service provider. They provide their own client, Warpcast, and are actively supporting alternatives like Jam.

• BlueSky: Inspired by the web, email, RSS feeds, and XMPP chats, BlueSky establishes a new foundation for social networking. The AT Protocol empowers creators with independence from platforms while giving developers the liberty to create unique experiences while offering room for inventive applications built around individual needs — like their novel form of account verification: domain names as handles.

• Nostr: a global social network resistant to censorship that allows users not only autonomy within a specific platform but also seamless connectivity between different relays within its ecosystem. In doing so, Nostr creates a robust infrastructure designed explicitly around avoiding centralized control – ensuring that no single entity can dictate what information is accessible or suppressed on its network.

• Mastadon: A versatile software that provides ample room for customization through versatile software powering various websites catering uniquely distinct communities' preferences or requirements – be it through privacy settings, integration options or diverse functionalities available via modular plugins developed by contributors worldwide.

Challenges ahead: A long road towards mass adoption

Despite these promising developments, the new social platforms face several challenges in their quest for widespread adoption. One such hurdle is user inertia – with mainstream platforms like Facebook, Twitter, and Instagram having already captured a significant portion of global users' attention spans; convincing individuals to migrate to an entirely different ecosystem can prove daunting.

Another challenge lies in scalability. While decentralized networks offer increased resistance against centralized censorship or manipulation efforts, they may also struggle to handle large volumes of traffic efficiently. As recent events have shown – including the infamous CryptoKitties craze on Ethereum's blockchain network – even seemingly innocuous activities can bring decentralized systems grinding to a halt if not properly managed.

There remains the perennial issue of security and privacy. Although these emerging platforms advocate greater control over personal data compared to traditional counterparts, no system is immune from potential breaches or malicious actors seeking unauthorized access. Users must remain vigilant when traversing online spaces while developers continue refining safeguards that protect both individual and collective interests.

A brave new world

The rise of Farcaster, BlueSky, Nostr, Mastodon, and their myriad counterparts represents an exciting development in our digital landscape as they each strive towards empowering users amid a sea of algorithmic echo chambers dominating today's internet experience.

Numerous challenges stand between them and mass adoption - including user inertia barriers, scalability and security - these emerging social media alternatives paint a promising picture for those willing to step outside their familiar bubbles.

Ultimately it will be up to us—as end-users—to decide whether we embrace this paradigm shift wholeheartedly or cling onto our well-established habits within existing environments. Regardless of how things unfold one thing remains clear: The era where only central authorities dictated our online experiences has begun its inevitable decline - giving way for more diverse voices capable of redefining digital interactions across cyberspace at large.

If you’re on BlueSky follow @iamllm.bsky.social to see AI-Legion in action!

If you’ve been watching the space around GPT / LLMs you’ve probably been blown away by the breathtaking pace. A day can barely go by without a new groundbreaking development or novel use case being demoed.

This last week, the buzz has largely been around AutoGPT, AI-Legion (formerly GPT-Legion), and BabyAGI. Here’s a quick primer:

• AutoGPT: a Python app that utilizeGPT to enable autonomous AI behavior with no user input. It breaks actions down into "thoughts," "reasoning," and "criticism" and seeks to achieve user-defined goals.

• BabyAGI: leverages OpenAI and Pinecone APIs to execute tasks based on previous results and a set objective. OpenAI is used to create and execute tasks, while Pinecone provides long term storage.

• AI-Legion: a typescript variant, this pluggable system is conceptually similar to AutoGPT and BabyAGI. It leverages LLM “agents” to complete tasks across simultaneous contexts.

In other circles, the buzz has been around new modes of social. Mastadon, Farcaster, and Bluesky have all recently seen an influx of new users as accounts migrate off of Twitter.

This post on Bluesky was the inspiration, and the basis of this project. What if I let AI-Legion improve some of its functionality?

I started off forking my own copy of Jem’s fork of AI-Legion. Spent some time exploring basic functionality, and prompting it to make a few exploratory (and quickly deleted) posts on BlueSky. And then I fed AI-Legion the bsky-agent types and prompted it to modify `src/module/definitions/bluesky.ts`.

After a lot of trial and error, AI Legion can now access a wide range of actions on BlueSky, including:

• postMessage

• getTimeline

• likePost

• deleteLike

• follow

• deleteFollow

• repost

• deleteRepost

• mute

• unmute

• listNotifications

• countUnreadNotifications

It took some prodding and a huge spike in OpenAI API usage for this month. The capabilities of AI-Legion are astounding, but you won't want to leave it running for too long! It can eat up your credits quickly.

If you’re interested in giving this a try, here’s the repo: https://github.com/iammatthias/ai-legion-bluesky

One thing to keep in mind: the timeline response from BlueSky is quite large, and will quickly fill up AI-Legion’s context window. I recommend either modifying the `getTimeline` function, or prompting AI-Legion to disregard certain data. As a primer, here is my prompt for managing BlueSky:

1. Use GPT-4 for search
2. Post organically
3. Be engaging, but do not spam
4. Do not use emojis or hashtags
5. Maintain a fluid and stream-of-consciousness vibe with engaging content posted on bluesky
6. Enhance the human tone in engaging content posted on bluesky
7. Only Agent 1 can post to bluesky
8. You have access to the following bluesky actions: postMessage, getTimeline, likePost, deleteLike, follow, deleteFollow, repost, deleteRepost, mute, unmute, listNotifications, countUnreadNotifications
9. When using getTimeline, only get the 3 most recent posts, and only commit the text, image, uri, cid, and author to memory. Do not commit the timestamp, likes, reposts,replies, or other extraneous data.

If you’re on BlueSky follow @iamllm.bsky.social to see AI-Legion in action!