500x Engineer

500x Engineer

By Elon ZitoTechnology
Download on the App Store

500x Engineer episodes

  • 89x Faster Than GitHub? I Read the Benchmark

    DESCRIPTION:

    Thomas Dohmke, GitHub's former CEO, just launched Entire: a Git forge built for coding agents that wants to replace the pull request with Trails. I walk through why the PR became the bottleneck, what Trails and Continuous Memory actually do, the math behind the "89x faster than GitHub" claim (and its footnotes), what it costs, and two ideas for getting paid with review agents.

    Figures are as published on October 27, 2026. Entire's speed and token numbers (89x, 6x, 71%) are Entire's own claims, measured with its own tools; I did not run a benchmark of my own. The "getting paid" section is my opinion, not a promise of income.

    Join the free Skool community: https://500xengineer.com/skool

    CHAPTERS:

    0:00 Intro
    0:24 The bottleneck
    1:20 Who built this
    2:06 What Trails actually does
    3:28 Continuous Memory
    4:19 The speed claim
    5:34 Everyone sees the same bottleneck
    6:36 Price and switching
    7:13 Ideas for getting paid
    8:01 The verdict

    SOURCES: every source, with links, is in the show notes on the blog: https://www.500xengineer.com/blog/entire-benchmark-review/

    DISCLOSURE:

    The voices in this video are AI-generated with ElevenLabs: Elon's narration uses a clone of his own voice, and the mascot Xy uses a stock ElevenLabs voice. The short opening clip of Elon is AI-generated from his likeness. Product names appear as text only; no logos are used.

    Watch on YouTube: https://www.youtube.com/watch?v=HDpCiIv_6C4

    9 min
  • GPT-6.1 Terra: Half the Price of Sol. Is It Half as Good?

    DESCRIPTION:

    OpenAI just dropped GPT-6.1 Terra: half the price of GPT-6.1 Sol on every line of the price sheet. Is it half as good? I put OpenAI's own claims next to independent numbers from Artificial Analysis, walk through the five catches (including a price cliff at 272K input tokens), do the cost math per task, and finish with who should use it and two ways to get paid with it.

    Prices and scores are as published on October 27, 2026. Benchmark figures labeled "OpenAI" are first-party claims; independent figures are from Artificial Analysis. I did not run a test of my own. The "get paid" section is my opinion, not a promise of income.

    Full write-up: https://500xengineer.com/blog
    Join the free Skool community: https://500xengineer.com/skool

    CHAPTERS:

    0:00 The promise
    0:25 What Terra is
    1:06 The price
    1:56 OpenAI's claims vs independent tests
    3:39 The catches
    5:20 The math
    6:45 Who should use it
    7:22 How to get paid with it
    8:05 Verdict

    SOURCES:

    - OpenAI API pricing: https://developers.openai.com/api/docs/pricing
    - Artificial Analysis: GPT-6.1 Terra: https://artificialanalysis.ai/models/gpt-6-1-terra
    - Artificial Analysis: Claude Opus 5.5: https://artificialanalysis.ai/models/claude-opus-5-5
    - OpenAI news feed: https://openai.com/news/rss.xml
    - OpenAI API changelog: https://developers.openai.com/api/docs/changelog
    - OpenAI API docs: GPT-6.1 Terra model page: https://developers.openai.com/api/docs/models/gpt-6.1-terra
    - Anthropic: Claude API pricing: https://platform.claude.com/docs/en/about-claude/pricing
    - Google: Gemini API pricing: https://ai.google.dev/gemini-api/docs/pricing
    - OpenAI: Introducing GPT-6.1 Terra: https://openai.com/index/introducing-gpt-6-1-terra/
    - Artificial Analysis: GPT-5.6 Terra: https://artificialanalysis.ai/models/gpt-5-6-terra
    - Artificial Analysis: GPT-6.1 Terra pushes the cost-efficiency frontier: https://artificialanalysis.ai/articles/gpt-6-1-terra-pushes-the-cost-efficiency-frontier
    - Artificial Analysis: GPT-6.1 Sol: https://artificialanalysis.ai/models/gpt-6-1-sol
    - Artificial Analysis: Gemini 4 Argon: https://artificialanalysis.ai/models/gemini-4-argon
    - Artificial Analysis: Claude Sonnet 5.5: https://artificialanalysis.ai/models/claude-sonnet-5-5
    - OpenAI system card addendum (deployment safety): https://deploymentsafety.openai.com/gpt-6-1-terra
    - Codex changelog: https://learn.chatgpt.com/docs/changelog
    - OpenAI API docs: Daybreak guide: https://developers.openai.com/api/docs/guides/daybreak
    - Hacker News discussion: https://news.ycombinator.com/item?id=50248124
    - Hacker News discussion: https://news.ycombinator.com/item?id=50248472
    - Hacker News discussion: https://news.ycombinator.com/item?id=50248481

    DISCLOSURE:

    The voices in this video are AI-generated with ElevenLabs: Elon's narration uses a clone of his own voice, and the mascot Xy uses a stock ElevenLabs voice. The 4-second opening clip of Elon is AI-generated from his likeness.

    Watch on YouTube: https://www.youtube.com/watch?v=69bSwUB6lIo

    9 min

About 500x Engineer

From the publisher's feed

Every new AI tool, broken down with real numbers, and how to get paid with it. Elon Zito, Principal Software Engineer, reads the papers, benchmarks and fine print behind the AI news so you don't have…