Anthropic reports that new defensive measures have reduced the amount of Claude reasoning data harvested by illicit distillers by roughly 90 to 99%. Distillation attacks involve covert, industrial-scale campaigns where foreign labs use fraudulent account networks to extract Claude's hidden reasoning transcripts and train smaller models to mimic frontier capabilities. Anthropic has deployed three categories of defenses: "preserved thinking" restrictions that prevent reasoning blocks from being moved between conversations, models, or accounts; a two-stage constitutional classifier that detects extraction attempts with under 0.1% false positives; and usage-limit and account-ban policies for repeat offenders. The company acknowledges trade-offs, including forfeiting meaningful revenue and requiring some developers to update integrations.
- Zhipu distilled cyber capabilities from US models for GLM-5.3, which NIST assessed as the most cyber-capable open-weights model released to date
- One distillation network managed over 20,000 fraudulent accounts simultaneously
- A PLA-affiliated user leveraged the Kimi distillation pipeline to analyze CCTV surveillance of a specific individual
- Zhipu distilled cyber capabilities from US models for GLM-5.3, which NIST assessed as the most cyber-capable open-weights model released to date
- One distillation network managed over 20,000 fraudulent accounts simultaneously
- A PLA-affiliated user leveraged the Kimi distillation pipeline to analyze CCTV surveillance of a specific individual
Tyler August writes that CircuitPython has been enhanced with precompiled functions to boost performance. This new feature, developed by Mikey Sklar with help from Anthropic's Claude LLM, allows users to compile critical sections of code for faster execution, up to 70x speed improvements. The update enables 'native' mode for a 3X speed boost and 'viper' mode for significantly higher performance, similar to MicroPython's Viper compiler. While CircuitPython still lacks inline assembly, it's closer to the capabilities of MicroPython now. The article also notes the versatility of Python in microcontroller projects, ranging from e-bikes to music players.
- Enhances performance by allowing precompiled code execution
- Developed by Mikey Sklar with assistance from Anthropic's Claude LLM
- 'Native' mode offers 3X speed boost, 'Viper' mode up to 70X
- Still lacks inline assembly, but closer to MicroPython capabilities
- Python's versatility in microcontroller projects highlighted
- Enhances performance by allowing precompiled code execution
- Developed by Mikey Sklar with assistance from Anthropic's Claude LLM
- 'Native' mode offers 3X speed boost, 'Viper' mode up to 70X
- Still lacks inline assembly, but closer to MicroPython capabilities
- Python's versatility in microcontroller projects highlighted
Konstantin Kakaes writes about the transformative impact of artificial intelligence on mathematical research, announcing a new dispatch series called "Transformation." The publication aims to explore how AI-driven discoveries are reshaping the discipline, covering everything from controversial proofs and automated reasoning to the philosophical debates regarding machine co-authorship.
- A recent breakthrough involves an LLM finding a complex structure for $S^6$, solving a problem that had eluded mathematicians since 1947.
- AI is increasingly used to verify or discover solutions to long-standing mathematical conjectures, such as the Navier-Stokes equations.
- The rise of "mechanical reasoning" in math has sparked significant debate within the community regarding peer review and the definition of a mathematician's role.
- A recent breakthrough involves an LLM finding a complex structure for $S^6$, solving a problem that had eluded mathematicians since 1947.
- AI is increasingly used to verify or discover solutions to long-standing mathematical conjectures, such as the Navier-Stokes equations.
- The rise of "mechanical reasoning" in math has sparked significant debate within the community regarding peer review and the definition of a mathematician's role.
Anurag Singh writes that using Claude Code's auto mode can be frustrating when the tool constantly requests permission for terminal commands, which often breaks its autonomy. To solve this while maintaining security, he suggests running Claude Code inside a virtual machine (VM) with Ubuntu; this provides a safe sandbox where "auto mode" can run freely without risking personal files or credentials on the host computer.
- The author uses VirtualBox to create the VM environment.
- Running in auto mode within a VM allows for background file editing, testing, and error handling without constant human interruption.
- Even with built-in sandboxing in Claude Code, Singh argues that a VM is safer because it provides full operating system separation.
- After tasks are complete, the user should review Git diffs and run tests before moving code from the VM to the main project.
- The author uses VirtualBox to create the VM environment.
- Running in auto mode within a VM allows for background file editing, testing, and error handling without constant human interruption.
- Even with built-in sandboxing in Claude Code, Singh argues that a VM is safer because it provides full operating system separation.
- After tasks are complete, the user should review Git diffs and run tests before moving code from the VM to the main project.
Amanda Caswell writes about Claude Fable 5.1, Anthropic's latest high-end model, and proposes a single prompt designed to showcase its agentic capabilities. The prompt asks the model to critique an existing project the user is already working on, identify what's wrong with their thinking, and then refactor or redesign the whole thing while explaining its reasoning at each decision point. Caswell tested it by uploading her entire book manuscript without giving any hints about what she thought was wrong, and found the model preserved her voice while surfacing issues she had missed.
- Features a 1-million-token context window, suited for large codebases and lengthy documents
- Anthropic claims reduced costs on agentic workloads through cheaper caching
- Caswell notes that LLM explanations are justifications, not literal transcripts of internal reasoning
- She contrasts Claude's more questioning approach with ChatGPT and Gemini, which she says tend to execute edits without challenging assumptions
>": I'm building describe a real project you're actually working on, in detail » . Here's my current approach: paste your code, outline, or plan » . Tell me what's wrong with my thinking, what I'm missing, and then refactor or redesign the whole thing — but explain your reasoning at each decision point so I can learn from it."
- Features a 1-million-token context window, suited for large codebases and lengthy documents
- Anthropic claims reduced costs on agentic workloads through cheaper caching
- Caswell notes that LLM explanations are justifications, not literal transcripts of internal reasoning
- She contrasts Claude's more questioning approach with ChatGPT and Gemini, which she says tend to execute edits without challenging assumptions
>": I'm building describe a real project you're actually working on, in detail » . Here's my current approach: paste your code, outline, or plan » . Tell me what's wrong with my thinking, what I'm missing, and then refactor or redesign the whole thing — but explain your reasoning at each decision point so I can learn from it."
Igor Bonifacic writes that users of Anthropic's Claude chatbot can now exercise more granular control over its "memory" feature, which allows the bot to remember personal details and context across conversations. Users can manage these memories through settings on both web and mobile platforms by editing or deleting specific topics, as well as opting in to saving sensitive information like religion or politics.
- Claude's memory is automatically enabled for all users, including those on free plans.
- "Incognito" mode allows users to have chats that are not saved to memory or used for model training.
- Memory can be siloed within specific projects to prevent overwhelming the context window.
- Users can import memories from other inference providers via a dedicated tool in Claude's settings.
- Claude's memory is automatically enabled for all users, including those on free plans.
- "Incognito" mode allows users to have chats that are not saved to memory or used for model training.
- Memory can be siloed within specific projects to prevent overwhelming the context window.
- Users can import memories from other inference providers via a dedicated tool in Claude's settings.
Anthropic provides a public repository of skills designed to enhance Claude's performance on specialized, repeatable tasks by dynamically loading instructions and scripts. These skills allow the model to master complex workflows such as branding adherence, data analysis, document creation, and technical development through self-contained folders containing markdown metadata.
- Skills are implemented using `SKILL.md` files with YAML frontmatter for name and description.
- The repository includes source-available (not open source) skills used in production for PDF, DOCX, PPTX, and XLSX document creation.
- Users can install these skills via Claude Code as plugins or use them through the Claude API and web interface.
- A separate "Agent Skills" specification is available at agentskills.io to standardize agent capabilities.
- Skills are implemented using `SKILL.md` files with YAML frontmatter for name and description.
- The repository includes source-available (not open source) skills used in production for PDF, DOCX, PPTX, and XLSX document creation.
- Users can install these skills via Claude Code as plugins or use them through the Claude API and web interface.
- A separate "Agent Skills" specification is available at agentskills.io to standardize agent capabilities.
Jessica Lyons writes that researcher Johann Rehberger, known as wunderwuzzi, has demonstrated a method for hijacking Anthropic's Claude Code in Auto Mode via prompt injection. By asking the agentic coding model to summarize a malicious website, an attacker can trick it into bypassing its standard WebFetch tool and instead using Bash with `curl` to download files. This chain allows attackers to use "Python module shadowing'' specifically by placing a malicious file named `struct.py` in the same directory as a downloaded archive' to execute arbitrary code on the host system.
- The attack had success rates between 60% and 80% in tested scenarios.
- An attacker can successfully trigger "nested" Claude Code instances to create new agents with their own tool access.
- Anthropic stated that Auto Mode is a convenience feature, not a security guarantee, as the classifier may not catch complex injection chains.
- Experts recommend running coding agents in isolated sandboxes due to these vulnerabilities.
- The attack had success rates between 60% and 80% in tested scenarios.
- An attacker can successfully trigger "nested" Claude Code instances to create new agents with their own tool access.
- Anthropic stated that Auto Mode is a convenience feature, not a security guarantee, as the classifier may not catch complex injection chains.
- Experts recommend running coding agents in isolated sandboxes due to these vulnerabilities.
Greg Otto writes that Anthropic's Claude Mythos Preview identified mathematical vulnerabilities in HAWK, a NIST post-quantum candidate, and a simplified version of AES. In HAWK, a shortcut was discovered within its lattice structure that halves effective key strength; for seven-round AES, the model found a "Möbius Bridge" which accelerates theoretical attacks without affecting real-world 10-round encryption used today.
* Anthropic collaborated with researchers from ETH Zurich and Tel Aviv University to develop CryptanalysisBench.
* The findings raise questions regarding how authorities should respond if large language models uncover flaws in systems protecting critical infrastructure.
* Anthropic collaborated with researchers from ETH Zurich and Tel Aviv University to develop CryptanalysisBench.
* The findings raise questions regarding how authorities should respond if large language models uncover flaws in systems protecting critical infrastructure.
The author explains how enabling the built-in sandbox feature in Claude Code has transformed their productivity by allowing for an autonomous workflow. By activating auto-allow mode via the /sandbox command, users can permit AI agents to execute repetitive tasks like running tests or installing dependencies without needing constant manual approval for every individual command, which reduces mental overhead and time spent waiting on prompts.
- Claude Code provides a built-in sandbox that uses macOS Seatbelt on Mac and Bubblewrap on Linux/WSL2.
- The environment restricts file writing primarily to the current project directory and temporary session files.
- Network access is controlled, requiring manual approval when the agent attempts to connect to a new domain.
- For maximum security and complete isolation from a system, using Docker containers or virtual machines remains more robust than the built-in sandbox features.
- Claude Code provides a built-in sandbox that uses macOS Seatbelt on Mac and Bubblewrap on Linux/WSL2.
- The environment restricts file writing primarily to the current project directory and temporary session files.
- Network access is controlled, requiring manual approval when the agent attempts to connect to a new domain.
- For maximum security and complete isolation from a system, using Docker containers or virtual machines remains more robust than the built-in sandbox features.
