korrents
Ben Vinegar

Ben Vinegar

@ben-vinegar · 22 positions · On ppll ↗

Co-founder of Modem, and before it VP of Engineering at Sentry. Joined Sentry as its founding engineer; builds hunk.dev and runs the DevTools Toronto meetup. Posts as @bentlegen.

Ben Vinegar did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

  1. coding agents

    to make *actually* good software, you have to use it a lot but many people are spending more time in their coding agents/factories than in the apps they're building - so they won't

    ↗@bentlegen on Xx.com

  2. 1 day earlier
  3. AI writing

    what a PR review of AI code looks like for me: 1) does it do anything remotely dangerous 2) does it touch files I would reasonably expect it to 3) do the tests cover the expected behaviour 4) does it follow architecture convention 5) [spot check code for slop]

    ↗@bentlegen on Xx.com

  4. 2 days earlier
  5. coding agents

    Whereas when you're, when you're ripping on just like a lower fidelity mock -ups that might be like 80 % fidelity that kind of tell you the shape, like you, it takes less tokens. The agent takes less time to generate it. It puts you on the better path going forward.
    spoken · machine transcript hear it at 26:07 · all korrents from this recording

    ↗Sentry Startup Spotlight with Ben Vinegar Founder of Modemyoutube.com 1st of 2 in this recording

  6. So I guess I guess that's my like weird take, which is there's an underserved market for understanding. It is hard to market because it's like you can't really put like a dollar or like a metric on it in the same way that you can tokens.
    spoken · machine transcript hear it at 33:06 · all korrents from this recording

    ↗Sentry Startup Spotlight with Ben Vinegar Founder of Modemyoutube.com 2nd of 2 in this recording

  7. 4 weeks earlier
  8. coding agents

    That uncovered many small issues and patched them - enough to feel like we were making progress - but it steered us away from the *real* problem There’s still no substitute for expertise

    ↗@bentlegen on Xx.com

  9. 6 days earlier
  10. open source

    my advice to people is like you know if you want to get into software um i actually encourage you to build open source software first and demonstrate that you can actually get anybody to use anything because it's really hard
    spoken · machine transcript hear it at 0:14:11 · all korrents from this recording

    ↗Is Agent Harness relevant in 2026 | Ben Vinegar (Co-founder, Modem.dev)youtube.com 1st of 2 in this recording

  11. innovation

    So to me, I just look at that as to say like, that's the indicators that we are at the beginning. And there's probably still a lot more innovation to happen.
    spoken · machine transcript hear it at 1:00:35 · all korrents from this recording

    ↗Is Agent Harness relevant in 2026 | Ben Vinegar (Co-founder, Modem.dev)youtube.com 2nd of 2 in this recording

  12. 7 weeks earlier
  13. LLMsRuby

    it does seem like long-term Ruby and Zig are dead. And what I mean is that if the LLMs are not choosing them over a long enough timeline, they're going to become like Louisiana French.
    spoken · machine transcript hear it at 0:42:15 · all korrents from this recording

    ↗State of Agentic Coding #7 with Armin and Benyoutube.com 1st of 4 in this recording

  14. It was a Cloudflare worker oddity. And you know what? There's no more Stack Overflow. There's no more people writing blog posts. There's no one writing, gee, I hit this painful problem with Cloudflare workers and here's how I solved it. So how does the agent index this?
    spoken · machine transcript hear it at 1:17:18 · all korrents from this recording

    ↗State of Agentic Coding #7 with Armin and Benyoutube.com 2nd of 4 in this recording

  15. Well, look, we don't need 400 3-column agentic coding multiplexers. We don't need that. The primitives are the bigger unlock to what's possible than the AI coding.
    spoken · machine transcript hear it at 1:25:34 · all korrents from this recording

    ↗State of Agentic Coding #7 with Armin and Benyoutube.com 3rd of 4 in this recording

  16. this like fast fashion, like fast fashion of software is what we're experiencing right now. where people are building something and they're like, hey, look at this. And if they don't, like, if people don't use it, they throw it away and go and try to find some other flash in the pan thing. Folks, my advice to you is have some conviction and work on things a little bit longer.
    spoken · machine transcript hear it at 1:28:17 · all korrents from this recording

    ↗State of Agentic Coding #7 with Armin and Benyoutube.com 4th of 4 in this recording

  17. 4 days earlier
  18. you get lulled into this false sense of security. But I've already experienced agents kind of like reason to themselves about why they gotta go and do something and seen, um, seen some bad effects of that. And I just, like, my position and the position of the company, for example, is we just, everything is gated. We don't just let agents go YOLO.
    spoken · machine transcript hear it at 0:26:24 · all korrents from this recording

    ↗Draw in your terminal! tmux + Terminal Maxxing w/ Ben Vinegar (Syntax)youtube.com 1st of 2 in this recording

  19. Linuxcoding agents

    I just wanna make a comment that like coding agents make you doing stuff on Linux way more approachable.
    spoken · machine transcript hear it at 0:33:16 · all korrents from this recording

    ↗Draw in your terminal! tmux + Terminal Maxxing w/ Ben Vinegar (Syntax)youtube.com 2nd of 2 in this recording

  20. 6 days earlier
  21. A pattern I'm seeing with AI debugging: it's easy to get stuck inside the model's search space. So you burn tokens & time chasing candidate fixes, while the real answer sits in context only you have ... but never explored, because you quietly surrendered your thinking.

    ↗@benv.ca on Blueskybsky.app

  22. 3 weeks earlier
  23. AI sometimes makes things too easy, and there's value in the pain.
    spoken · machine transcript hear it at 1:33:00 · all korrents from this recording

    ↗State of Agentic Coding #6 with Armin and Benyoutube.com

  24. 5 months earlier
  25. LLMs

    Hate to say it, but the functional programmers were right. LLMs love code with explicit inputs/outputs and no side effects.

    ↗@bentlegen on Xx.com

  26. 4 weeks earlier
  27. open source

    Feels like the demand for OSS hasn't felt this low in a while: 1. People can just codegen what they want 2. Companies will use whatever gets them to market faster to capitalize on AI – if it's a black box so what

    ↗@benv.ca on Blueskybsky.app

  28. 7 weeks earlier
  29. I've come to accept AI will write the majority of code.

    ↗@benv.ca on Blueskybsky.app

  30. 2 months earlier
  31. LLMs

    IMO the job increasingly becomes translating what you're thinking to a form the agents/LLMs understand. The tools will improve, sure, but I wouldn't bet on a future where they know how to read your mind.

    ↗@benv.ca on Blueskybsky.app

  32. 7 months earlier
  33. SaaS

    When SaaS products grow and the architecture starts to break down, two types of devs emerge: 1. Those who believe the system is beyond repair and needs to be totally rebuilt 2. Those who put their heads down and fix it one piece at a time I've only seen group #2 be successful.

    ↗@benv.ca on Blueskybsky.app

  34. 1 day earlier
  35. "API stability" is an underrated killer feature of frameworks & libraries, IMO.

    ↗@benv.ca on Blueskybsky.app

  36. 19 months earlier
  37. JavaScript

    I think React's single greatest accomplishment is that it convinced web developers to finally stop bending over backwards in trying to separate business and presentation logic on the client.

    ↗@benv.ca on Blueskybsky.app