CtrlK
BlogDocsLog inGet started
Tessl Logo

ainativedev/latest-aidevcon-speakers-london-2026

AI Native DevCon 2026 London — all conference sessions as interactive skills

71

Quality

89%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Overview
Quality
Evals
Security
Files

quotes.mdtalk-wotherspoon-humans-vs-slop/

Notable Verbatim Quotes — Humans vs. Slop

Each quote is a direct extract from transcript.md. Use these for citations; verify line context in the transcript before quoting.

On the framing / "slop"

  • "I use the word slop, but I don't actually really like that word too much." — Intro & framing
  • "the war of our generation" — MC intro (apparent slip / joke before correcting the title)

On the old social contract

  • "every pull request or code that was put up to your repository was by someone who probably thought about it. Was actually handwriting code." — The old world
  • "you're kind of expected to read the docs, make sure that whatever is breaking isn't on your fault, it's actually the library or the framework that you are using." — The old world

On the AI shift

  • "you don't know whether or not that pull request is being put up by someone's agent, whether they've even actually looked at the code" — How AI is changing it
  • "code is essentially free. You know, it's just a prompt away." — How AI is changing it

On subsidized inference

  • "you're paying $20 or $200, but you're potentially getting thousands of dollars actual inference out of those subscriptions." — Subsidized inference
  • "a single prompt did over 60 million in tokens, which would regularly be $200 if you were paying for the actual API cost. So from a $30 plan, theoretically, you would have been able to get over $30,000 worth of inference." — Subsidized inference

On the maintainer cost

  • "maintaining code isn't free. Generating code is free like we talked about, but maintaining it is not. And that's really kind of where this battle is now being fought." — Maintaining code isn't free
  • "GitHub released that over 45 million pull requests were merged per month in 2025... I think last month they said it was over 200 million pull requests. So we're already seeing a 5x right there." — Maintaining code isn't free

On drive-by PRs and trust

  • "drive by PR really is someone confident. They had no expectation that they were actually going to have to follow up or do anything... So you just have a prompt and forget it." — Main issue 1
  • "Nowadays, I don't know. Gemini told me to or Claude told me to. So now that the thing is you've not actually trust there." — Main issue 3

On the new rules

  • "we require you to put up an issue first before you can put up a pull request. So this kind of eliminates 90% of those drive by PRs" — New rule 1
  • "don't just commit the context files for Claude. If you're using Claude, that's perfect. But you should actually add an agents.md as well." — New rule 4
  • "what would you use over 50% of the time? And that's kind of the number that we use to gate what... [is] disabled or enabled by default." — Q4 / skill management

On community experiments

  • "any pull request or issues during that time. Will get automatically closed and say, hey... we're on open source vacation." — OSS Vacation
  • "trusted maintainers or contributors can vouch for other people... And then the flip side, you can actually get denounced. So bots or people who have put up sloppy code can get denounced and then they get blocked." — Vouch
  • "he said PR quality has gone way up. Like the vouch system. But he actually is still seeing the PR. So it's really just filtering out the bad ones." — Vouch (on Mitchell Hashimoto / Ghostty)

On the future

  • "don't give me the code. Just give me the prompt that you use to generate the code and I'll go do it myself." — Prompts as PRs
  • "the future is really moving towards collaboration. It's not just humans. It's not just agents. It's really a blend of the two." — New playbook summary
  • "update your contributing.md files. Normally you would put how for humans to actually go ahead and interact with your code. I would actually add a section to kind of what is your contribution guidelines for agents or for AI." — Takeaways

talk-wotherspoon-humans-vs-slop

README.md

tile.json