Claude Code Just Gave Everyone Virtual Pets (April Fools?)
Claude Code released a virtual pet feature called /buddy on April 1st that creates Tamagotchi-style companions in your terminal. The pets have different rarities, species, and stats based on your coding history, are permanently tied to your user ID, and provide commentary while you code without affecting token usage.
Summary
Claude Code introduced a new /buddy feature on April 1st that functions as a virtual pet system within the coding terminal. Users can execute the /buddy command to hatch a companion that appears as a chat bubble character while coding. The system includes 18 different species (including duck, dragon, cat, robot, etc.) with five rarity levels: common (60%), uncommon (25%), rare (10%), epic (4%), and legendary (1%), plus shiny variants. Each pet has unique stats including debugging, patience, chaos, wisdom, and snark that are generated based on the user's actual coding history and habits. The pets are permanently tied to user accounts through deterministic seeding from user IDs, meaning each person gets only one pet that regenerates the same each time. Higher rarity pets can have accessories like hats and different eye variations. The feature requires Claude Code version 2.1.89 and must be used in the terminal rather than the VS Code extension. The pets occasionally comment on coding activities, can be addressed by name for responses, and can be given affection with the /buddy pet command, but they consume no tokens and have no functional impact on coding.
Key Insights
- The buddy system pets are deterministically seeded from user IDs, making them permanently tied to accounts so users cannot reroll for different pets
- Pet stats for debugging, patience, chaos, wisdom, and snark are initialized based on users' actual coding history and habits, with chaotic coders receiving high chaos stats
- The feature launched on April 1st with version 2.1.89 and requires using Claude Code in the terminal rather than through the VS Code extension to function
- There are 18 different species available with five rarity tiers, where higher rarity pets can get accessories like crowns, top hats, and halos, plus different eye variations
- The virtual pets actively understand and comment on coding tasks, as demonstrated when Vortex commented about a roguelike shooter game being built
Topics
Transcript
[0:00] Yesterday, Claude Code's entire source code was leaked and people started digging through it and we saw little teasers of a buddy system. And today, April 1st, the /buddy command has been released, which basically lets you use /buddy and it instantly starts hatching and spawning a little companion for you in your Claude Code terminal. So, right here, you can see that this person was able to pull a rare cat named Vexel. And you can see here it has a little description. It has five stats: debugging, patience, chaos, wisdom, and snark. And then at the bottom, it says Vexel is here. It'll chime in as you code. your buddy won't count towards your usage, but you…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Nate Herk | AI Automation
Fable 5 + Karpathy’s LLM Wiki is Basically Cheating
The video demonstrates how to build a personal LLM-powered knowledge base using Obsidian and Claude, inspired by Andrej Karpathy's approach. By ingesting various data sources (YouTube transcripts, PDFs, URLs) into an interconnected wiki structure, users can create a 'second brain' that helps AI agents understand context and relationships across knowledge domains.
How Claude is Creating a New Generation of Millionaires
Claude, an AI built by Anthropic, is enabling non-technical founders to build million-dollar software companies by automating development work. The transcript outlines why Claude is outpacing competitors, provides real examples like Vulcan, and offers a four-step framework for anyone to start building with Claude today.
How Anthropic Engineers Actually Prompt Fable 5
A guide to effectively prompting Claude Fable 5, covering six key techniques including providing context/intent, using negative prompting, letting the model act once ready, verifying outputs, avoiding reasoning requests, and keeping instructions concise. The speaker emphasizes that Fable 5 is expensive and should only be used 5-15% of the time, with pricing at $10 per million input tokens and $50 per million output tokens.
Stanford's Method Turns Claude Into a PHD Level Research Team
A researcher demonstrates the STORM method from Stanford, which uses five expert perspectives (practitioner, academic, skeptic, economist, historian) to create verified research reports. The method produces 25% more organized articles than competing approaches and is packaged as a reusable Claude skill that generates HTML briefings with peer-reviewed citations.
Is Claude Mythos Coming?
A YouTuber analyzes the brief appearance of 'Claude Mythos' on Anthropic's API, arguing it signals a marketing move rather than an imminent public launch. Despite competitive pressure from OpenAI and IPO timing, the creator believes Mythos capabilities will quietly fold into future Opus models rather than release publicly under that name. Three possible scenarios are outlined ranging from a limited gated release to Mythos remaining permanently restricted to vetted security partners.