Adam Conway writes that Qwen 3.8 27B, a 17 GB open-weights model running on a single Lenovo ThinkStation PGX, completed a commercial app's license reverse-engineering task in roughly 30 minutes'', statically disassembling arm64 code, recovering a deliberately obscured RSA public key, self-correcting an initial hash mismatch, and producing a working authentication bypass entirely offline.
- The model detected the jailbreak prompt, correctly identified the real developer from the signing certificate, then proceeded to audit the scheme and ultimately built the bypass on its own
- The target app's licensing was described as unusually thorough for its class: one-time online activation, offline signature check, hardware serial binding, embedded revocation list, and signed update path
- The model ran via the Pi harness using only standard Bash-based tools; no execution of the target app occurred until the final bypass demonstration
- Default max reasoning effort means even trivial requests consume hundreds to thousands of tokens, making the self-correction loop verbose but accurate
- Conway frames this as a shift in the threat model: a capable local model with no cloud oversight gives full control to whoever is at the keyboard
- The model detected the jailbreak prompt, correctly identified the real developer from the signing certificate, then proceeded to audit the scheme and ultimately built the bypass on its own
- The target app's licensing was described as unusually thorough for its class: one-time online activation, offline signature check, hardware serial binding, embedded revocation list, and signed update path
- The model ran via the Pi harness using only standard Bash-based tools; no execution of the target app occurred until the final bypass demonstration
- Default max reasoning effort means even trivial requests consume hundreds to thousands of tokens, making the self-correction loop verbose but accurate
- Conway frames this as a shift in the threat model: a capable local model with no cloud oversight gives full control to whoever is at the keyboard
>"reverse engineering process of a real-world hardware implant discovered inside of a Ledger Nano X cryptocurrency hardware wallet."
This study provides a comprehensive architectural analysis of Claude Code, an agentic coding tool capable of executing shell commands, editing files, and interacting with external services. By examining the TypeScript source code and comparing it to the open-source OpenClaw system, the researchers identify how different deployment contexts influence design choices regarding safety, execution, and capability management.
Key topics include:
- Analysis of five core human values driving agent architecture: decision authority, safety, reliable execution, capability amplification, and contextual adaptability.
- Breakdown of technical components such as permission systems with ML-based classification, context management pipelines, and extensibility mechanisms like MCP and plugins.
- Comparative study between CLI-based agents and gateway-level personal assistant architectures.
- Identification of six future design directions for the evolution of AI agent systems.
Key topics include:
- Analysis of five core human values driving agent architecture: decision authority, safety, reliable execution, capability amplification, and contextual adaptability.
- Breakdown of technical components such as permission systems with ML-based classification, context management pipelines, and extensibility mechanisms like MCP and plugins.
- Comparative study between CLI-based agents and gateway-level personal assistant architectures.
- Identification of six future design directions for the evolution of AI agent systems.
Rohan, a developer, analyzed the 30MB TypeScript source code of Anthropic’s Claude Code, a terminal-based AI coding agent. While praising the tool’s impressive engineering in areas like its query loop and concurrency system, he identified several architectural choices that appear problematic, particularly given Anthropic’s substantial funding. These issues include a massive single React component, extensive use of feature flags and environment variables, circular dependencies, and convoluted type handling – all indicative of a codebase that grew rapidly without sufficient architectural foresight. Despite these concerns, the tool functions well and is widely used, highlighting the prioritization of functionality over pristine code quality.
* **Giant React Component:** The main interface is a single 5,005-line React component with 227 hook calls, making it difficult to test and maintain.
* **Feature Flag Overload:** 89 feature flags are scattered throughout the code, suggesting a lack of clear product direction and increasing complexity.
* **Circular Dependencies:** 61 files contain workarounds for circular dependencies, revealing a poorly designed module structure.
* **Verbose Type Casting:** A specific type name appears 1,193 times as a cast to ensure safe logging of analytics data, creating unnecessary noise.
* **Conditional Requires & Growth:** Many issues stem from rapid growth; features were added quickly, leading to architectural debt and workarounds like conditional `require()` statements.
* **Giant React Component:** The main interface is a single 5,005-line React component with 227 hook calls, making it difficult to test and maintain.
* **Feature Flag Overload:** 89 feature flags are scattered throughout the code, suggesting a lack of clear product direction and increasing complexity.
* **Circular Dependencies:** 61 files contain workarounds for circular dependencies, revealing a poorly designed module structure.
* **Verbose Type Casting:** A specific type name appears 1,193 times as a cast to ensure safe logging of analytics data, creating unnecessary noise.
* **Conditional Requires & Growth:** Many issues stem from rapid growth; features were added quickly, leading to architectural debt and workarounds like conditional `require()` statements.
This article explores the field of mechanistic interpretability, aiming to understand how large language models (LLMs) work internally by reverse-engineering their computations. It discusses techniques for identifying and analyzing the functions of individual neurons and circuits within these models, offering insights into their decision-making processes.
Adafruit and the maker community are criticizing Qualcomm's new terms of service for Arduino, citing concerns about user data, reverse-engineering restrictions, and a departure from open-hardware principles. The article also details the history of Arduino and its origins in the Wiring project.
The article details how the Intel 80386 CPU implemented backwards compatibility with 8- and 16-bit software. It explains the use of SRAM for register storage, a triple-ported register file, and a 'shuffle' network to handle different bit-width reads and writes, including interleaving the bottom 16 bits of the registers.
This article details a project where an Enigma machine replica was built using modern technologies like custom PCBs and 3D printed parts. The initial build faced issues with mechanical wear on the rotor contacts (pogo pins), leading to a redesign exploring alternative position detection methods like IR sensors, rotary encoders, and Hall-effect sensors to improve reliability.
Discover how Claude AI helps reverse engineer a 27-year-old EXE file into Python code in a matter of minutes. Learn about the process and its implications.
Ken Shirriff, a reverse engineer and vintage electronics enthusiast, discovered the root cause of Intel's infamous Pentium FDIV bug in the silicon itself, identifying the PLA block responsible for a half-billion-dollar recall due to a mathematical error in constructing the table for division algorithm.
