seangoedecke.com

Latest posts

• Insider amnesia

  Feb 23, 2026
• What's so hard about continuous learning?

  Feb 23, 2026
• LLM-generated skills work, if you generate them afterwards

  Feb 17, 2026
• Two different tricks for fast LLM inference

  Feb 15, 2026
• On screwing up

  Feb 11, 2026
• Large tech companies don't need heroes

  Feb 08, 2026
• Getting the main thing right

  Feb 05, 2026
• How does AI impact skill formation?

  Jan 31, 2026
• You have to know how to drive the car

  Jan 26, 2026
• How I estimate work as a staff software engineer

  Jan 24, 2026
• I'm addicted to being useful

  Jan 20, 2026
• Crypto grifters are recruiting open-source AI developers

  Jan 17, 2026
• The Dictator's Handbook and the politics of technical competence

  Jan 05, 2026
• 2025 was an excellent year for this blog

  Jan 03, 2026
• Grok is enabling mass sexual harassment on Twitter

  Jan 02, 2026
• Software engineers should be a little bit cynical

  Dec 28, 2025
• You can't design software you don't work on

  Dec 27, 2025
• Nobody knows how large software products work

  Dec 24, 2025
• AI detection tools cannot prove that text is AI-generated

  Dec 05, 2025
• How good engineers write bad code at big companies

  Nov 29, 2025
• Becoming unblockable

  Nov 26, 2025
• Why it takes months to tell if new AI models are good

  Nov 22, 2025
• Only three kinds of AI products actually work

  Nov 16, 2025
• Writing for AIs is a good way to reach more humans

  Nov 14, 2025
• To get better at technical writing, lower your expectations

  Nov 09, 2025
• Is it worrying that 95% of AI enterprise projects fail?

  Nov 03, 2025
• Why do AI models use so many em-dashes?

  Oct 30, 2025
• Mistakes I see engineers making in their code reviews

  Oct 25, 2025
• Should LLMs just treat text content as an image?

  Oct 21, 2025
• What have we learned about building agentic AI tools?

  Oct 19, 2025