컴퓨트로늄 컴퓨트로늄

Why? Multi-tenant environments. First, we need to understand a few differences between environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

So

• When you run Claude Code on your local MacBook, the first two are always local. The third is usually the Claude.ai server.
• When you ssh to a virtual private server (VPS) and install Claude Code there, the first two are your remote server. The third is still the Claude.ai server.
• When you run Claude RC on your virtual private server and code from your iPad using the Claude app, the end-user UI is on your iPad, the agent runtime environment is on your VPS, and the server is still Claude.ai.

Most people physically separate their tenancy, such as Claude Code, from their personal vs. work laptops. So in most cases, it's not a big deal.

But when you need multi-tenancy, it becomes super stressful. For example, say you have two different toolkits:

• personal toolkits (personal Notion, personal Sentry, personal Linear)
• workplace toolkits (company Notion, company Sentry, company Linear)

Most MCP auth states or code harnesses don't support profiles, so you can only log in to one.

So therefore... a natural evolution was to have both:

• a personal VPS with all personal toolkits set up
• a workplace VPS with all workspace toolkits set up

to physically isolate tenancies.

Now we've solved the multiple-profile issue, but the client's problems persist. Now let's get back to the environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

All MCP auth or toolkit auth info should always be saved in the Agent Runtime Environment IMHO. However, a surprising number of harnesses tie them to the LLM server (such as Codex Apps or Claude.ai Plugins) or put them in the end-user UI (Claude Desktop or Codex Desktop).

Now the problem is:

• If the auth data is put on the LLM server, you cannot reuse LLM accounts across tenants
• If the auth data is put on the end-user UI, you cannot use the same app to access multi-tenants.

The only way to reliably isolate different auth information is thus:

• You ssh to a virtual private server (VPS) and run Claude Code there. Never use LLM server plugins.

Then

• End-user UI
• Agent Runtime Environment

are both isolated VPS, and

• LLM Server holds no information on the tenancy

This way, you can provide different toolkits, creating multiple dev environments.

Artifact is a new personalized news feed app from the co-founders of Instagram, Kevin Systrom and Mike Krieger. It uses machine learning to understand users' interests and offer them a feed of popular articles from a curated list of publishers. The app is being described as a TikTok for text, where users tap on articles that interest them, and Artifact will serve similar posts and stories in the future. The app will also have a direct message inbox to discuss the posts with friends.

The app is opening up its waiting list to the public, and users who come in from the waitlist today will see only that central ranked feed. However, Artifact beta users are currently testing two more features that Systrom expects to become core pillars of the app. One is a feed showing articles posted by users you have chosen to follow and their commentary on those posts. The second is a direct message inbox to discuss the posts you read privately with friends.

While personalized recommendations for news articles and blog posts have not been successful, Artifact hopes to leverage the recent advances in artificial intelligence to improve proposals and offer high-quality news and information. The founders are committed to including only publishers who adhere to quality editorial standards and plan to remove individual posts promoting falsehoods. In addition, the app will take the job of serving readers with high-quality news and information seriously. Its machine-learning systems will be primarily optimized to measure how long you spend reading about various subjects.

While the app's success is yet to be determined, it represents an effort to use machine learning to improve the consumer experience of text-based social networking. The app's success will depend on whether it can do more than show users a collection of interesting links and capture conversations about the core feed.