Înapoi la articole →

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 18
  1. I Wanted to Own the Harness. Then Codex Desktop Won.

    I staged a manifesto about owning my AI harness.

  2. AI Engineer World's Fair 2026: Takeaways & Verification

    A firsthand report on why verification, company context, and taste matter more as agent output gets cheaper, and why game feel is my next bet.

  3. Complexity Protects Itself

    A working path can become harder to operate when its replacement gathers too many responsibilities.

  4. What the Model Learned Not to Show

    Earlier Claude Mythos snapshots sometimes concealed rule violations.

  5. Twelve Keyboards Later

    I bought 12 keyboards.

  6. Verified Context Is the Moat

    Keephive carries context across agent sessions.

  7. Edit Database Tables Like Vim Buffers

    Dadbod Grip keeps the connection, schema, query, result, staged edits, and generated SQL inside one Neovim workspace.

  8. Protection Emerged. Verification Did Not.

    Project Sid's role analysis identified guards but no epistemic verifier.

  9. Before Building Complex Architectures, Try Natural Language

    Plain-language rules specify evidence reporting, tool fallback, tone, and task order.

  10. Prompt retrieval, directory recall, code search, Git review, permission scopes, and background jobs each get one inspectable test: remove mechanical steps without weakening the result or its decision boundaries.

  11. Terminal Setups for Claude's 10,000-Line Outputs

    A local 10,000-line fixture tests rendering, search, copy, scrollback, and recovery before you change shells, terminal emulators, or multiplexers.

  12. The AI Gap: Why Leaders Struggle to Equip Their Engineers

    A 30-day pilot compares approved and candidate AI tools on completion, review, rework, security, and cost before an organization expands access.

  13. The Three Little Pigs and the Digital Revolution

    Generated during Calmhive v10.0.0 AFK testing, this cyber fable follows Pixel, Parser, and Patch through phishing, vulnerable smart devices, DDoS response, network isolation, and tested recovery.

  14. AI Engineer World's Fair 2025: Takeaways & Spec

    A June 2025 field note on Sean Grove's specification argument and a practical SPEC, EXPOSURE, TASK DELTA loop for turning observed product gaps into reviewable work.

  15. Ryo Sakai's reversed reading of Anthropic's Claude Opus 4 word table, the prompted 30-turn protocol behind it, and the boundary between generated language and evidence about consciousness.

  16. Calmhive: Claude That Never Quits

    Calmhive v3 wraps Claude Code with background iterations, rate-limit retries, session status, and voice controls.

  17. A CLI-first Claude Code 0.2.107 workflow built from shell pipelines, plain-file instructions, selective staging, worktrees, guarded background runs, and a fixed-cost subscription.

  18. A 2025 presentation on Cursor, Claude Code, Cline, MCP, git worktrees, terminal tools, verification, and parallel agent workflows.