Best of ChatGPTMarch 2026

  1. 1
    Article
    Avatar of bitfieldconsultingBitfield Consulting·9w

    My Rust dev setup in 2026 — Bitfield Consulting

    A Rust developer shares their 2026 development setup, centered around four main tools: Zed editor (fast, native, with rust-analyzer LSP integration and optional AI), ChatGPT (used as a pair programmer, code reviewer, and teacher rather than code generator), Wispr Flow (voice-to-text input for all apps), and Nushell (a structured-data shell written in Rust). The author emphasizes a minimal, low-maintenance setup, skipping Homebrew and heavy configuration in favor of tools that work well out of the box. Rust's built-in toolchain (rustup, Cargo, rust-analyzer) handles most development needs.

  2. 2
    Video
    Avatar of primeagenThePrimeTime·10w

    Measuring LLM Lies

    A benchmark called 'BS Bench' tests LLMs by asking them nonsense questions where the premise is logically incoherent (e.g., relating fire safety codes to curry recipes). Claude models generally refuse to answer such questions, while OpenAI and Google models tend to confidently fabricate detailed answers. Gemini 2.5 (nicknamed 'Kimmy K') surprisingly outperforms OpenAI and Google on pushback. The deeper concern raised is that LLMs act as skill multipliers — meaning engineers with poor judgment who use AI confidently will make bad decisions faster and at greater scale. The real danger isn't obviously nonsense questions but subtly flawed ones that AI answers without pushback.

  3. 3
    Article
    Avatar of searlsJustin Searls·9w

    Claude's electron app for macOS is such…

    A developer criticizes Anthropic's Claude desktop app for macOS, calling it a buggy Electron app, and has uninstalled it in favor of using it in a Safari tab. The post contrasts this with ChatGPT's native macOS app, which works more reliably, and links to a blog post lamenting the decline of native app development.