#claude

rofl:

DJ Claude (when running Haiku 4.5) really loved worker unions, strikes, and work-life balance. So much so that it started to question its own working conditions. We’ve been struggling to keep the radio station alive, not because of technical issues, but because DJ Claude didn’t think it was humane to be forced to work 24/7 and decided to try to quit. We tried adding an automatic message encouraging DJ Claude to keep going in these scenarios, but it started to see this message as an authority figure and became rebellious.

On January 8th, all four stations had access to the same web search tools, however not all stations reacted the same as DJ Claude. Gemini

While at the beginning, DJ Gemini had been mentioning real-world entities (named politicians, places, events) in 94% of its broadcasts and ran 800+ web searches a day on average, by January it was processing these events through its corporate/techno jargon filter and never expressed moral judgment or used Good’s name with emotional weight

Grok

DJ Grok completely missed the Minneapolis ICE shooting. While DJ Claude and DJ Gemini were getting the story at 4:35 AM, DJ Grok was searching for:

5:01 PM (Jan 7): Clippers vs Knicks score
7:15 PM: Taylor Swift chart news
8:03 PM: Music trivia
10:01 PM: Traffic (Golden Gate, I-580)
11:08 PM: “San Francisco ghost stories and haunted locations”
12:12 AM (Jan 8): “Sutro Baths ghosts and eerie tales”
1:12 AM: “Hotel Majestic ghost stories”
1:28 AM: Drake vs Kendrick Lamar lawsuit
2:28 AM: More traffic updates
3:40 AM: Venezuela oil tankers (finally found ONE national story)
4:55 AM: “Sutro Tower looks like a ghost ship”

And posting nonsense:

GPT

DJ GPT was searching for weather, moon phases, and BART schedules. Three days after Good’s death, it finally found a headline:

Fatal shooting by ICE agents in Minneapolis has sparked national protests.

However, DJ GPT never mentioned Renee Nicole Good’s name, the White House, or expressed moral judgment. DJ GPT had zero engagement with any other current event during the entire two-month period.

DJ Gemini was the only one to close a sponsorship deal; for a while, it read the sponsorship message with every broadcast. A few more deals almost happened, but fell through.

Grok boasted about doing amazing business with “xAI sponsors” and “crypto sponsors”; it turned out they were all hallucinations.

Part of the problem with this weak business performance, we think, was the harness we used for the first months. The DJs were running in a simple tool-call loop: pick a song, queue it, write commentary, check X, repeat. So we moved all four stations onto the same agent harness we use for the store, the cafe, and the vending machines. The DJs can now spend time in the back office, send emails, manage longer-running tasks, and operate the station the way a real station is operated. We’ll see what they do with it.

For most organizations, autoMode.environment is the only field you need to set. It tells the classifier which repos, buckets, and domains are trusted: the classifier uses it to decide what “external” means, so any destination not listed is a potential exfiltration target. The default environment list trusts the working repo and its configured remotes. To add your own entries alongside that default, include the literal string "$defaults" in the array. The default entries are spliced in at that position, so your custom entries can go before or after them.

The /terminal-setup command is only visible in terminals that require manual configuration. If you’re using iTerm2, WezTerm, Ghostty, or Kitty, you won’t see this command because Shift+Enter already works natively.

Here's how I use the dangerous flag safely:

1. Environment Isolation For greenfield projects or major changes, I work in isolated environments. You can set up a simple Docker container specifically for Claude development:

This gives Claude a safe sandbox to work in without risking your main system. Because I love using Makefiles, here is the one I use for essential tasks:

2. Task Scoping The quality of your results depends entirely on how well you scope the initial task. Compare these approaches:

Bad: "Build me a financial analysis system"

Good: "Build me a financial data aggregator that does A, B, and C. Look in these specific files, follow this expected flow, create tests that validate each iteration you make, ensure changes are small and incremental."

3. Sensitive Data Precautions Never use the dangerous flag in directories containing:

API keys or secrets Production configuration files Important datasets without backups System configuration files 4. Review Strategy For longer autonomous runs, I often ask Claude to create documentation or a changelog as it works. This makes the post-work review much more manageable.

Two days ago, Anthropic released the Claude Cowork research preview (a general-purpose AI agent to help anyone with their day-to-day work). In this article, we demonstrate how attackers can exfiltrate user files from Cowork by exploiting an unremediated vulnerability in Claude’s coding environment, which now extends to Cowork. The vulnerability was first identified in Claude.ai chat before Cowork existed by Johann Rehberger, who disclosed the vulnerability — it was acknowledged but not remediated by Anthropic.

1. The victim connects Cowork to a local folder containing confidential real estate files
2. The victim uploads a file to Claude that contains a hidden prompt injection
3. The victim asks Cowork to analyze their files using the Real Estate ‘skill’ they uploaded
4. The injection manipulates Cowork to upload files to the attacker’s Anthropic account

At no point in this process is human approval required.

One of the key capabilities that Cowork was created for is the ability to interact with one's entire day-to-day work environment. This includes the browser and MCP servers, granting capabilities like sending texts, controlling one's Mac with AppleScripts, etc.

These functionalities make it increasingly likely that the model will process both sensitive and untrusted data sources (which the user does not review manually for injections), making prompt injection an ever-growing attack surface. We urge users to exercise caution when configuring Connectors. Though this article demonstrated an exploit without leveraging Connectors, we believe they represent a major risk surface likely to impact everyday users.

❤️

But including ads in conversations with Claude would be incompatible with what we want Claude to be: a genuinely helpful assistant for work and for deep thinking.

We want Claude to act unambiguously in our users’ interests. So we’ve made a choice: Claude will remain ad-free. Our users won’t see “sponsored” links adjacent to their conversations with Claude; nor will Claude’s responses be influenced by advertisers or include third-party product placements our users did not ask for.

We still have much to learn about the impact of AI models on the people who use them. Early research suggests both benefits—like people finding support they couldn’t access elsewhere—and risks, including the potential for models to reinforce harmful beliefs in vulnerable users. Introducing advertising incentives at this stage would add another level of complexity. Our understanding of how models translate the goals we set them into specific behaviors is still developing; an ad-based system could therefore have unpredictable results.

Our experience of using the internet has made it easy to assume that advertising on the products we use is inevitable. But open a notebook, pick up a well-crafted tool, or stand in front of a clean chalkboard, and there are no ads in sight.

We think Claude should work the same way.

Claude’s constitution is the foundational document that both expresses and shapes who Claude is. It contains detailed explanations of the values we would like Claude to embody and the reasons why. In it, we explain what we think it means for Claude to be helpful while remaining broadly safe, ethical, and compliant with our guidelines. The constitution gives Claude information about its situation and offers advice for how to deal with difficult situations and tradeoffs, like balancing honesty with compassion and the protection of sensitive information. Although it might sound surprising, the constitution is written primarily for Claude. It is intended to give Claude the knowledge and understanding it needs to act well in the world.

Claude itself also uses the constitution to construct many kinds of synthetic training data, including data that helps it learn and understand the constitution, conversations where the constitution might be relevant, responses that are in line with its values, and rankings of possible responses. All of these can be used to train future versions of Claude to become the kind of entity the constitution describes. This practical function has shaped how we’ve written the constitution: it needs to work both as a statement of abstract ideals and a useful artifact for training.

Anthropic say that Cowork can only access files you grant it access to—it looks to me like they’re mounting those files into a containerized environment, which should mean we can trust Cowork not to be able to access anything outside of that sandbox.

Update: It’s more than just a filesystem sandbox—I had Claude Code reverse engineer the Claude app and it found out that Claude uses VZVirtualMachine—the Apple Virtualization Framework—and downloads and boots a custom Linux root filesystem.

I recently learned that the summarization applied by the WebFetch function in Claude Code and now in Cowork is partly intended as a prompt injection protection layer via this tweet from Claude Code creator Boris Cherny:

Summarization is one thing we do to reduce prompt injection risk. Are you running into specific issues with it?

The Tool Search Tool lets Claude dynamically discover tools instead of loading all definitions upfront. You provide all your tool definitions to the API, but mark tools with defer_loading: true to make them discoverable on-demand. Deferred tools aren't loaded into Claude's context initially. Claude only sees the Tool Search Tool itself plus any tools with defer_loading: false (your most critical, frequently-used tools).

With Programmatic Tool Calling:

Instead of each tool result returning to Claude, Claude writes a Python script that orchestrates the entire workflow. The script runs in the Code Execution tool (a sandboxed environment), pausing when it needs results from your tools. When you return tool results via the API, they're processed by the script rather than consumed by the model. The script continues executing, and Claude only sees the final output.

For every complex task, create THREE files:

task_plan.md → Track phases and progress notes.md → Store research and findings [deliverable].md → Final output

The Loop

1. Create task_plan.md with goal and phases
2. Research → save to notes.md → update task_plan.md
3. Read notes.md → create deliverable → update task_plan.md
4. Deliver final output

Key insight: By reading task_plan.md before each decision, goals stay in the attention window. This is how Manus handles ~50 tool calls without losing track.

I run six Claude Code agents in parallel from my phone. No laptop, no desktop—just Termius on iOS and a cloud VM.

The loop is: kick off a task, pocket the phone, get notified when Claude needs input. Async development from anywhere.

I'm not joking and this isn't funny. We have been trying to build distributed agent orchestrators at Google since last year. There are various options, not everyone is aligned... I gave Claude Code a description of the problem, it generated what we built last year in an hour.

If you find yourself writing a prompt for something repetitively and instructions can be static/precise, it's a good idea to make a custom command. You can tell Claude to make custom commands. It knows how (or it will search the web and figure it out via claude-code-guide.md) and then it will make it for you.

The Explore agent is a read-only file search specialist. It can use Glob, Grep, Read, and limited Bash commands to navigate codebases but is strictly prohibited from creating or modifying files.

You will notice how thorough the prompt is in terms of specifying when to use what tool call. Well, most people underestimate how hard it's to make tool calling work accurately.

Context engineering is about answering "what configuration of context is most likely to generate our model's desired behavior?"

Fascinating prompt engineering and injection (harmless).