Înapoi la articole →

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 181
  1. I spent two weeks on runtime engineering for on-device voice cloning, then ran a one-hour forced-choice blind test against real recordings and scored 8/8 identifying the fake. p = 0.0039.

  2. Apple's Speech framework handles 34 languages.

  3. Three weeks, 21 releases, 20,299 lines of Go and 19,906 lines of tests.

  4. Three months.

  5. DailyVox builds a model of one person from their own journal, on their phone.

  6. RSS subscribers read 10x more posts per delivery than email, churn at 1/8th the rate, and require zero infrastructure to support.

  7. A plaintext file at the website root that tells LLM crawlers what they should index.

  8. Spec-driven development is being sold as a new methodology for the agent era: write a precise spec, let the agent build to it.

  9. Your final-year machine learning project is the first real portfolio piece most Indian students will have, and almost everyone treats it as a checkbox to clear instead.

  10. Every machine learning career path guide for India draws the same neat ladder of certifications and job titles.

  11. I took a clean backtest live and the equity curve inverted inside a week.

  12. DailyVox runs the AI on your phone, not on my server.

  13. The agent that wrote the code should not be the one that decides it is correct.

  14. The bottleneck is me

    Three and a half years of following one cost curve, and it has landed in my own chair with a physical symptom.

  15. Three years of a public trade log, now a live PnL dashboard on feaws.

  16. For twenty-five years the bottleneck in software was writing the code.

  17. Fourteen SVG motifs, one template, build-time PNG render.

  18. On-device AI eliminates the per-request API cost.

  19. My son asked for Minecraft.

  20. Eighteen years of accumulated backlinks.

  21. The TwinEngine reads a year of your journal entries and builds a model of how you think, what you care about, and what triggers your worst weeks.

  22. On September 4, 2022, someone dropped seven zero-byte PHP files at the root of my WordPress install.

  23. Every list of machine learning interview questions gives you the textbook answer to 'what is overfitting.'

  24. Why making your trading strategy public almost never destroys it, and why the edge from publishing usually exceeds the edge you lose.

  25. An assistant that forgets you every session is a toy.

  26. After 18 years on WordPress — through plugin rot, database corruption, spam floods, and one too many 'critical update' emails — I rebuilt intrepidkarthi.com from scratch on Astro, Markdown, and Vercel.

  27. Most AI projects students put on a resume were good signals in 2020 and are dead ones now.

  28. Before slippage or fees or psychology gets its turn, the data itself lies.

  29. When I rebuilt this blog in 2026 from a cPanel SQL dump, 27 posts came back clean. 58 did not.

  30. Going through the old WordPress wp_options table during the archive migration, I found the original name of this blog.

  31. A walkthrough of the feaws.xyz whitepaper in plain English.

  32. I have been writing a diary for 20 years.

  33. Books I Have Read

    A complete list of books I've read over the years — from fiction to business strategy, self-help to thrillers.

  34. Apple's strictest privacy label.

  35. I’ve Been Writing a Diary for 20 Years.

  36. The home screen widget is the highest-leverage retention surface on iOS.

  37. Apple's CryptoKit makes authenticated encryption look like a three-line API.

  38. Same prompt, same audio, two providers.

  39. I co-authored a machine learning book, so this will sound strange coming from me: most people trying to learn ML should read fewer books, not more.

  40. Syncing user data through Apple's CloudKit while ensuring Apple itself cannot read it.

  41. Most retail traders end a losing week by closing the broker screen.

  42. Eight years apart, two fraud-detection problems.

  43. When agents open pull requests faster than any human can read them, reading every diff stops being a strategy.

  44. Six characters in a single property flip the entire trust model of a speech-recognition app.

  45. I started working on Feaws in late 2025, not because I thought I could beat the market, but because the existing tools frustrated me.

  46. The fresher's trap: no ML job without ML experience, no ML experience without a job.

  47. Twenty years of writing a daily diary, then six weeks of silence, then voice notes.

  48. USD stablecoins moved $11 trillion in 2024.

  49. Apple's NaturalLanguage framework looks clean in the WWDC slides.

  50. Set temperature to zero and the model is supposed to be deterministic.