Tag
An author shares their experience with a tiny e-ink reader, encountering display bugs after installing open-source firmware, and using GPT-6 Astra in Codex to diagnose and fix the issues.
A user instructs Claude AI to change an 'Add to Cart' button to blue without altering other elements, demonstrating AI assistance in UI customization.
An experiment to elide implementation details from code in Emacs using a pipeline with OhmJS and RWR, aiming to improve code readability by focusing on structure.
The author discusses challenges with large code diffs caused by AI use in code reviews and seeks advice on strategies to handle this while maintaining human comprehension.
This paper proposes ProSE-Plan, a Bayes-adaptive planner that improves AI assistance by considering user evaluability under bounded rationality, using proposals as probes to learn preferences and enhance decision-making.
A podcast episode on the Pragmatic Engineer podcast featuring Casey Muratori discussing software performance and the use of AI to assist in learning Assembly.
A user on X seeks assistance from X and Space xAI to address content theft by another user who fails to provide attribution.
The article discusses how AI assistance has simplified the creation of fast JIT compilers with sub-microsecond compile times, demonstrated through a Rust-based regular expression engine example.
Linus Torvalds describes a challenging debug session where an AI assistant provided significant help but also showed limitations by suggesting to give up, which he overcame through persistence.
The article shares a method using an agent.md file to define coding style preferences for LLM-assisted development, improving code quality by reducing repetitive feedback.
The author discusses their journey in personal finance tracking and introduces plain text accounting as a reliable method using plaintext files and double-entry bookkeeping, preferred over traditional finance apps like Rocket Money and Origin.
A user shares that Claude AI helped optimize their Ubiquiti UniFi Wi-Fi setup, resulting in 54% faster Wi-Fi speeds and 25% faster wired speeds after a 25-minute process.
The author reflects on his journey from manually typing code on a vintage Macintosh to embracing AI-powered code completion tools like Copilot and Claude, concluding that while the AI industry is problematic, the technology itself can be useful.
Humanly is a configurable writing platform that records the writing process to provide traceable evidence of human-AI collaboration, with features like sealed certificates and anomaly detection.
This paper investigates why some developers experience significant coding productivity improvements from AI assistance while others see little to no benefit, exploring factors that may explain the variance.
A developer reflects on the trade-off between using AI to write code faster versus understanding the code deeply, and questions how to balance AI assistance with genuine learning.
This research paper investigates how AI advice reduces people's willingness to express uncertainty, even when the advice is wrong and accuracy is incentivized, altering metacognitive thresholds.
A blog post detailing the author's experience using LLMs to configure MikroTik networking equipment, including tips and best practices.
Android Studio Quail 2 is now stable, introducing parallel AI agent chats, integrated LeakCanary memory leak detection with 5x faster profiling, and Gemini-powered crash fixes.
This paper presents a case study where a mathematician directed an AI to formalize the mean-field derivation of the Vlasov equation in the Lean proof assistant, framing the process as a strategy game. The formalization was completed in about a month, with the AI executing proofs under human guidance.