all

wiki/sources/2026-07-14-sebastian-eugene-interview.md

@@ -35,7 +35,7 @@
 - **Entities:** [[sebastian]] · [[eugene]] · [[virtido]] · [[claude-code]] · [[hermes]] (Eugene references it among his tools)
 - **Concepts:** [[harness]] · [[enterprise-ai-reality]] · [[seniority-and-the-junior-squeeze]] · [[product-ownership]] · [[connections-as-moat]] · [[decoupling-identity-from-profession]] · [[code-as-throwaway]]
 - **Related sources:** [[2026-07-14-skills-based-on-git]] (harness definition + BYO-harness from the practitioner side) · [[2026-07-14-everything-we-knew-about-software-has-changed]] (identity baggage, code-as-throwaway)
-- **Raw reference (not ingested):** `raw/sources/Ideas for webinar.md` echoes many of these (harness, connections, "describe problems not waterfalls," Daniel, HR search demo).
+- **Raw reference (authored deliverable, not a source):** `raw/notes/Ideas for webinar.md` echoes many of these (harness, connections, "describe problems not waterfalls," Daniel, HR search demo).
 
 ## Open Questions
 

wiki/sources/2026-07-28-agentic-engineering-10x-developer.md

@@ -0,0 +1,62 @@
+# Agentic Engineering, explained by a 10x developer — Thorsten Ball
+
+#source
+
+## Source Metadata
+
+- **Date:** YouTube interview (publication date not stated in source), 42:33 — https://www.youtube.com/watch?v=FU5_kpTAVDo
+- **Raw path:** `raw/sources/Agentic Engineering, explained by a 10x developer.md`
+- **Source type:** podcast/video interview (conclusions doc)
+- **Speaker:** [[thorsten-ball]] — founding engineer at [[amp]] (Sourcegraph); author of *Writing an Interpreter in Go* / *Writing a Compiler in Go*
+- **Interviewer:** David Andre
+- **Ingestion date:** 2026-07-28
+
+## Core Claims
+
+- **The interesting variables moved.** Not "which model" or "how do I read every line," but: where does the information the agent needs live, how agent-friendly is your codebase/workflow, and what do you actually want to build. "The dominant variable in output quality is now the information you put in."
+- **Shed weight.** Kill anything that only made sense before agents — backlogs, CI that re-runs the agent's own tests, IDE extensions, admin panels, local dev. AMP kills its own features publicly and calls itself "AMP Frontier Corporation." See [[shedding-weight]].
+- **99% of AMP is written by AI**, and that is compatible with high taste. "Most of slop comes from humans not having good product. With AI they can just build trash products faster." Slop = lack of ideas and playfulness, not an AI defect.
+- **Build for the agent, not the human.** No human should fill out forms; anything a human can do on your site an agent should be able to do; ideally **bring your own agent**. See [[build-for-the-agent-not-the-human]].
+- **Software becomes bespoke** by two mechanisms: remixing existing software you don't upstream ([[emacsification-of-software]]) and building internal tools that used to be an Excel file ([[explosion-of-internal-software]]).
+- **Async by default.** An *orb* — a remote sandbox tied to one conversation — packages thread + agent + computation + diff in one shareable URL. Delegate, do something else, and **ask for proof** because you're waiting anyway. See [[async-by-default]].
+- **He uses no skills, no MCP servers, no custom slash commands.** The only thing that matters to him is where the agent gets its information: training data (lossy, stale) plus the context window (your prompt, the codebase, `AGENTS.md`). *This directly contradicts the vault's skills spine — logged below and on [[skills-as-memory]].*
+- **First-principles thinking is now the top skill.** "Everyone becomes an architect"; the value is seeing the workflow underneath the request and knowing solutions from other industries.
+
+## Key Evidence / Details
+
+- **Model choice:** once you have Fable 5 / GPT-5.6 Sol or equivalent, diminishing returns on which you pick, and on the effort level (medium vs high vs ultra). "If you're mad your model doesn't use camelCase, rethink your software engineering, not the model." AMP's default is medium.
+- **AMP's setup:** installed as a PWA from `ampcode.com`; a low/medium/high/ultra dial mapping to model + sub-agent choice; sub-agents **Oracle** (reviewer/advisor) and **Painter** (images); meta-agent **Puck** that controls other agents, spawns orbs, messages them, runs flows. GPT, Anthropic and GLM models all supported. Agent-to-agent communication shipped "last Friday."
+- **The hand-coding poll:** Thorsten polled the team with options 99%+, 90–99%, <90% — he didn't expect anyone under 80%. The one engineer who said "I still write a bunch by hand" landed at ~95% when pushed.
+- **Taste at AI speed:** he had AI generate **15 versions** of the orb icon (Braille characters, different styles, 18 palettes) and picked one. AMP news imagery came from turn-by-turn Midjourney with two colleagues while reading Moby Dick.
+- **The admin panel that dies:** he built a food-ordering app for a local club from a menu photo in 3 × 5-minute iterations; the agent also built an admin UI for prices and spelling. "I'm never going to open that. I'll just send another photo and say 'fix the pricing.'" A lot of admin UI existed only so that no code had to change.
+- **The remix:** forked a diff viewer called **hunk**, told AMP "add Gruvbox dark hard theme, add file-checkoff in sidebar, compile, drop it in `~/bin`" — two minutes of agent time, no reason to upstream.
+- **Internal software:** at his 20-person club he encoded the ordering process in ~2 hours of *phone typing*. Two variables separate winners from losers: knowing how to use agents, and **having the token budget** to do it.
+- **The printer anti-example:** asked to build an app so a tablet prints a paper receipt for the kitchen, he pushed back — "Why do you need a printer? Why not a second tablet?"
+- **Don't benchmark against the 1%:** Mitchell Hashimoto (Ghostty, GPU-accelerated terminal emulator) is cited in every online debate, but most software is CRUD, "MySQL and something-something," which agents handle fine.
+- **His prompt structure** (porting Puck to the CLI): set the standard ("look at how it's implemented in web UI") → state intent → riff on the design → give explicit process ("research, document, sit down and think, compile what you learned, then come up with a good idea") → set sub-agent economics ("Fable is expensive, it scares me — use GPT models for the implementation"). "This is how I would talk to a senior engineer. This is the Slack message I'd send."
+- **Velocity:** shipping velocity up in 4 weeks; designer Tim "never fixed so many paper cuts"; screenshot a bug → orb returns a fix → spot check → merge. A demo change was **shipped to production live during the podcast**.
+- **Predictions:** local dev goes away; model distinctions matter less ("a button with which you can spawn a John Carmack"); unclear what software survives remixability; infra margins get eaten (15+ sandbox providers racing to zero); everyone moves up a level of abstraction.
+
+## Connections
+
+- **Entities:** [[thorsten-ball]] (new) · [[amp]] (new) · [[claude-code]] (peer harness) · [[theo-browne]] (closest ally in the corpus)
+- **Concepts created:** [[shedding-weight]] · [[build-for-the-agent-not-the-human]] · [[emacsification-of-software]] · [[explosion-of-internal-software]] · [[async-by-default]]
+- **Concepts reinforced:** [[context-as-scarce-resource]] (information > tuning; the token-budget variable) · [[code-as-throwaway]] (99% AI-written at a real company) · [[make-more-cheap-code]] (15 icon variations; ask for proof) · [[product-ownership]] (first-principles thinking, everyone an architect) · [[harness]] (AMP as a second reference harness; Oracle/Painter/Puck) · [[seniority-and-the-junior-squeeze]] (what took 2–3 years to teach is now a 30-second output)
+- **Concepts contested:** [[skills-as-memory]] and [[evolution-of-agent-tooling]] (he skips the whole progression) · [[leave-less-room-for-imagination]] (model choice as a lever — he says stop tuning; Eugene selects 4.7 over 4.8)
+- **Related sources:** [[2026-07-24-youre-reading-way-too-much-code]] and [[2026-07-14-everything-we-knew-about-software-has-changed]] (Theo — same strategic register, same slop-is-human stance); [[2026-07-14-sebastian-eugene-interview]] (the enterprise counterweight to "kill your process"); [[2026-07-21-larysa-interview]] (his `AGENTS.md`-only approach is exactly what leaves Larysa's memory gap unsolved)
+- **Named but not in the vault:** Mitchell Hashimoto, Ghostty, hunk, Sourcegraph, Midjourney, Cloud9, Quinn (AMP CEO), Riverside
+
+## Open Questions
+
+- **Does "no skills, no MCP" generalize, or is it a property of his situation?** He works daily in one codebase he controls, with a company harness he helped build and a team-maintained `AGENTS.md`. The vault's skills case is strongest for people who move across many ad-hoc tasks and cannot encode context in a codebase (HR, BA). Neither side is tested against the other. Status: tentative.
+- **What replaces the token budget as a constraint?** He names it as one of two winner/loser variables but says nothing about who pays for it — the missing economics of [[explosion-of-internal-software]].
+- All ratios (99% AI-written, the team poll) are self-reported from inside the company that sells the agent. Status: tentative.
+- If admin panels and forms die, what does a non-technical person operate? Thorsten's answer is "prompt the agent," which assumes the prompting skill the corpus's HR interviews say is the actual bottleneck ([[levels-of-ai-usage]]).
+- "Local dev is going away" is a prediction from a company selling remote sandboxes, and sits against [[eugene]]'s consolidated local workspace pitch ([[harness]]). Status: tentative.
+
+## Change Impact on Wiki
+
+- Created 5 concepts: [[shedding-weight]], [[build-for-the-agent-not-the-human]], [[emacsification-of-software]], [[explosion-of-internal-software]], [[async-by-default]].
+- Created 2 entities: [[thorsten-ball]], [[amp]].
+- Updated [[skills-as-memory]] and [[evolution-of-agent-tooling]] with the corpus's first credible *rejection* of the skills abstraction (recorded as a contradiction, not smoothed).
+- Updated [[context-as-scarce-resource]] (information > tuning; token budget), [[code-as-throwaway]] (99%-AI-written datapoint; slop-is-human), [[make-more-cheap-code]] (variations-not-answers; ask-for-proof), [[product-ownership]] (first-principles as the top skill), [[harness]] (AMP; the minimal-harness position), [[seniority-and-the-junior-squeeze]] (the collapse of hand-taught senior knowledge), [[enterprise-ai-reality]] (token budget as a new access divide), [[leave-less-room-for-imagination]] (his prompt structure as a worked example; model-tuning tension), [[personal-ai-operating-system]] (the fourth layer — tools you build for yourself), [[claude-code]] (AMP as peer harness), [[theo-browne]] (ally cross-link), [[overview]] (9→10 sources; new "frontier side" of the through-line), `index.md`.

wiki/sources/2026-07-29-what-if-we-vibe-code-it.md

@@ -0,0 +1,51 @@
+# А что если наВайб-Кодить? (What If We Vibe-Code It?)
+
+#source
+
+## Source Metadata
+
+- **Date of material:** 2026 (references tweets from March and July 2026)
+- **Raw path:** `raw/sources/А что если наВайб-Кодить.md`
+- **Source type:** viewer's conclusions from a YouTube video (5:31), Russian; https://www.youtube.com/watch?v=zBcWcignqng
+- **Author:** unknown (a developer; his company uses Datadog and pays "literally millions a year" for it)
+- **Ingestion date:** 2026-07-29
+
+## Core Claims
+
+1. **Writing code was never the bottleneck — and never the cost.** Developers could always have written their own Jira or Datadog; they didn't because they didn't *want to run the result*. AI removes the writing cost, which was ~zero of the total, and leaves the real cost untouched.
+2. **The cost of software is maintenance, not development.** The problem starts after the first user: bugs, regressions, feature requests, logs, monitoring, on-call, uptime responsibility.
+3. **An internal service is an internal business.** A company that vibe-codes its own tracker/logger is either switching businesses or running two IT businesses at once — bad for the company (pays for one product, team builds another) and for the developer (two jobs, blamed for both).
+4. **"I can write it in a week" ≠ "it's worth writing."** Between those two statements sit years of support. The vendor's price buys the removal of operational load, not the code.
+5. **The pendulum case:** two tweets months apart — March 2026, a company builds its own Jira clone and migrates to it; July 2026, back to buying a tracker (Linear) because nobody wanted to carry the in-house product. "Assemble in two weeks — easy; carry it forward — impossible."
+6. **A build-vs-buy checklist** for the AI era: size of the dependency (small, non-evolving libraries — fine to rewrite); does it need ongoing support (if yes, it's a separate project); what operational load does it add; is the business ready to open a second IT business inside itself. If the answers are bad, stay on the paid service — even with Claude / Antigravity / Codex at hand.
+7. **Self-correction:** the author retracts his own earlier claim that "many services will die because of AI" — he now says he was wrong.
+
+## Key Evidence / Details
+
+- The Jira→Linear pendulum (claim 5) is the source's only external evidence; both tweets are second-hand and the company identification is fuzzy ("the same or a similar company"). Status: tentative.
+- The author's own company is living the case study: pays millions/year for Datadog, is building an in-house replacement while also evaluating cheaper vendors — i.e. he criticizes the pattern from inside it, not from abstention.
+- The checklist (claim 6) is prescriptive, not observed — the author's recommendation, not a documented practice.
+
+## Connections
+
+- Creates [[maintenance-is-the-real-cost]] — the source's central concept, new to the vault.
+- Direct counterweight to [[explosion-of-internal-software]] and [[emacsification-of-software]]: both pages already flagged "maintenance is assumed away" as their weakest point; this source is the first to make that objection its whole thesis, with a named failure case.
+- Sharpens the boundary of [[code-as-throwaway]] / [[make-more-cheap-code]]: throwaway code is safe *because it never has users*. The trap begins exactly where code stops being throwaway — the first user makes it a service.
+- Agrees with the vault's spine from an unexpected angle: "writing code was never the bottleneck" is the same premise as [[harness]]-over-model and Theo's verification bottleneck — the sources disagree only about *which* non-writing cost dominates (verification vs. maintenance).
+- Counters [[thorsten-ball]]'s prediction range: his club app passes the author's checklist (small, no SLA, no external users), but his "teams will remix Riverside" prediction is exactly what the pendulum case punishes.
+
+## Open Questions
+
+- Where is the threshold? The checklist says "small, non-evolving libraries — yes; services with users — no," but the interesting zone is between: a 20-person club app, an internal HR knowledge base, a personal fork in `~/bin`.
+- Does the maintenance objection survive agents doing the maintenance? The author assumes ops load lands on humans; the corpus's outer-loop material ([[agentic-loops]], [[async-by-default]]) implies agents could carry some of it. Nobody in the corpus has evidence either way.
+- Who is the author, and does his in-house Datadog replacement ship or die? The pendulum predicts die.
+
+## Change Impact on Wiki
+
+- Created [[maintenance-is-the-real-cost]] (new concept).
+- [[explosion-of-internal-software]]: the "nobody owns the result" uncertainty upgraded from self-criticism to a sourced contradiction; scoping added (the club app passes the source's own checklist).
+- [[emacsification-of-software]]: the "maintenance is assumed away" objection now has a source and a failure case.
+- [[code-as-throwaway]]: boundary bullet added — throwaway is safe because unshipped; first user converts code into a service.
+- [[thorsten-ball]]: contradiction added (pendulum case vs. his remix-and-build predictions).
+- [[overview]]: divergence list and frontier-side bullet updated with the build-vs-buy counterweight.
+- [[2026-07-28-webinar-theses]]: scoping note added to T5 (the thesis survives — its examples are checklist-safe — but gains an honest boundary).