← Înapoi la Urmăritori

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 19
  1. How I use AI to help me write

    AI is a helpful writing tool for me.

  2. The release of Kimi K3 has opened a fresh round of angst and confused discourse.

  3. I had my first encounter with a political spambot this week: a polite robot named Emma texted me wanting to talk about Israel.

  4. An ever-increasing volume of debug investigations, document writing, and code is written by robots.

  5. Coding agents have no moat

    It's been a rough few months for Anthropic.

  6. Sora is dead.

  7. Is the Future of AI Local?

    Debate about whether the explosion of datacenter buildout will prove to be a worthwhile investment centers on two scenarios: AI adoption accelerates, the datacenter investment pays out AI adoption is not as fast as forecasted, and it doesn't.

  8. The design of AI memory systems

    For me, the question of memory is the most interesting subfield of AI.

  9. This Twitter thread was an interesting read: The TLDR of the snafu is: OpenClaw bot makes PR to matplotlib Maintainer Scott Shambaugh sees via the bot's website that it is a bot, explains that they do not accept bot contributions, declines PR Bot feels (s…

  10. How to Write Good (Short) Docs

    "I would have written a shorter letter, but I did not have the time." — Mark Twain1 Overview This post describes how to write a short document for your teammates.

  11. MCP is a Fad

    Overview Model Context Protocol (MCP) has taken off as the standardized platform for AI integrations, and it's difficult to justify not supporting it.

  12. Optimize for Humans

    I recently wrote about optimizing repos for AI, and since then I've been maintaining separate docs for humans (README, contributing guides) and AI agents (.cursorrules, CLAUDE.md, etc.).

  13. Optimizing repos for AI

    A colleague recently complained to me about the hassle of organizing information in AGENTS.md / CLAUDE.md.

  14. A reshaped learning curve Before AI, learners faced a matching problem: learning resources have to be created with a target audience in mind.

  15. Add Autonomy Last

    A core challenge of using LLM's to build reliable automation is calibrating how much autonomy to give to models.

  16. For LLM-based applications to be truly useful, they need predictability: While the free-text nature of LLMs means the range of acceptable outcomes is wider than with traditional programs, I still need consistent behavior: if I ask an AI personal assistant…

  17. Advice for New Grads

    This is a brief overview of my advice for new grads and junior software engineers.

  18. OpenAI launched its GPT Store this week.

  19. MemGPT Meta-Functions

    MemGPT is an interesting project which provides GPT agents with unbounded memory.