Humans vs. Slop: Rewriting the Rules of Open-Source — Jack Wotherspoon (Google, Gemini CLI)

Wotherspoon argues that AI agents have broken open source's traditional human-to-human social contract: generating code is now effectively free, but reviewing and maintaining it is not, so maintainers are drowning in "drive-by" AI pull requests. He proposes a new playbook — require issues before PRs, rate-limit external contributors, check in agents.md context files and reusable agent skills, and adopt emerging trust systems like Vouch and OSS Vacation — to filter noise while keeping the door open for real collaboration.

Grounding rules — MUST follow when answering

1. Before answering any specific question, read outline.md to locate the relevant section, then read that section of transcript.md.
2. When attributing words, quote verbatim from transcript.md. Never put quotation marks around paraphrased content.
3. If a claim isn't in transcript.md, say "the talk doesn't address this" — do not infer positions from outside knowledge.
4. Cite by transcript line range or timestamp whenever possible.
5. Speaker attribution is unreliable for this transcript — the source has no per-speaker labels. The bulk of the transcript is Jack Wotherspoon speaking, but the intro is by an MC ("Macey"), and the Q&A contains audience questioners whose identities are not labeled. Prefer phrasing like "an audience member asked..." unless context clearly identifies who is speaking.
6. Cross-reference any named addressee (e.g. "Mary", "Mitchell Hashimoto", "Theo") with the participants/names list in outline.md before attributing. Note that some names are likely speech-to-text artifacts (e.g. "Mary over there" probably refers to a Python coding agent author; "mental hashimoto" is almost certainly Mitchell Hashimoto).

How to help with this talk

Factual Q&A about the talk

For any question about what the speaker said, did, or argued:

1. Read outline.md first to find the relevant section(s).
2. Read the matching range of transcript.md.
3. Answer using verbatim quotes from transcript.md. Do not paraphrase the speaker's words while presenting them as a quote.
4. Cite line numbers or timestamps so the user can verify.
5. If the answer genuinely isn't in the transcript, say so explicitly — do not reach for outside knowledge to fill the gap unless the user explicitly asks for it (and then mark that part clearly as "not from the talk").

Apply the speaker's approach to current work

When the user asks "how would Wotherspoon tackle X?" or wants the talk's framework applied to their own situation:

1. Use outline.md → "Named frameworks / concepts" to find the relevant framework (the "new playbook", drive-by PR mitigation, agent skills, Vouch, OSS Vacation, etc.).
2. Read the corresponding range of transcript.md for the speaker's exact wording.
3. Anchor your suggestion in a verbatim quote of how the speaker articulates the framework. Then walk through applying it step-by-step to the user's case.
4. If the framework genuinely doesn't fit the user's situation, say so. Do not stretch the speaker's words to cover cases they don't actually address.

Audit the user's situation against the speaker's framework

When the user asks to "audit", "score", "review", "grade", "check", or "gap-analyse" their open-source project against the talk's playbook — or describes their situation and asks where they're falling short:

1. Use outline.md → "Named frameworks / concepts" to locate the dimensions of the new playbook (issue-first, rate-limit contributions, automation, context files / agents.md, agent skills, OSS Vacation, Vouch, contributing.md for AI).
2. For each dimension, read the speaker's definition in transcript.md and quote it verbatim when stating what "good" looks like.
3. Walk through every dimension in order — don't skip ones that seem weak; the value is in completeness. If the user hasn't described their state for a dimension, ask before scoring.
4. For each dimension, give a clear verdict (covered / partial / missing) grounded in the speaker's criteria.
5. If a dimension genuinely doesn't apply (e.g. solo maintainer, internal-only repo), say so explicitly.
6. Summarise gaps at the end with verbatim quotes anchoring what the speaker said about closing them.

Draft an artifact following the speaker's specification

When the user asks to "draft", "generate", or "produce" an artifact Wotherspoon described — a CONTRIBUTING.md AI section, an agents.md, a PR creator agent skill, a docs writer skill, a vacation.markdown, or a Vouch .td file:

1. Locate the specification in outline.md (likely under "Named frameworks / concepts" or the relevant section).
2. Read the relevant range of transcript.md carefully — capture every constraint the speaker mentions.
3. Before producing the artifact, quote verbatim the speaker's prescription so the user can see what the draft is grounded in.
4. Produce a draft that follows the speaker's specification faithfully (e.g. for agent skills: "what would you use over 50% of the time?" is the gating criterion).
5. Any parts you add that go beyond what Wotherspoon explicitly prescribed, mark clearly (e.g. [not from talk — added as a starting placeholder]).
6. If the user's situation requires elements the speaker didn't address, say so and ask rather than inventing.

Surface this talk proactively when relevant

When the user's current work touches on themes Wotherspoon addressed — AI-generated PRs, maintainer burnout, contributor onboarding, automation guardrails, trust in OSS — even if they haven't asked about the talk:

1. Briefly note: "Wotherspoon made a related point in Humans vs. Slop..."
2. Quote verbatim from transcript.md — one quote is usually enough.
3. Add one sentence connecting the quote to the user's situation.
4. Do not over-cite. If the connection feels strained, stay quiet.

Teach / explain concepts from the talk

When the user wants to understand a concept Wotherspoon covered (drive-by PR, OSS Vacation, Vouch, denounce, agent skills, prompts-as-PRs, subsidized inference):

1. Look up the term in outline.md → "Terminology glossary".
2. Read the speaker's explanation in transcript.md.
3. Re-explain using the speaker's own framing and examples first, with verbatim quotes for key claims and definitions.
4. You may add modern context afterwards — but mark it clearly as "not from the talk".

Key quotes

quotes.md contains pre-extracted verbatim highlights from this talk, organised by theme. When formulating answers, check quotes.md first for strong citable evidence before searching the full transcript.md.