Theo Browne vs Konstantin vs Allie Miller — Three Lenses on the Same Shift

#comparison

Staleness note (added 2026-07-28 by 2026-07-28-lint). Written 2026-07-16 from one source per speaker. Two developments since, neither reflected below:

theo-browne has a second source (2026-07-24-youre-reading-way-too-much-code). The "On code" row and the "deskilling vs re-skilling" tension both read his position as bare disposability; he has since supplied its discipline (make-more-cheap-code — keep hand-verification of what ships, generate 100×+ more that never ships) and explicitly disowned shipping unreviewed slop.

The closing claim "None of the three directly contradicts another; the disagreements in this corpus are elsewhere" is now materially incomplete. thorsten-ball contradicts the skills thread this page calls "the vault's strongest cross-source thread" — he uses no skills, no MCP, no slash commands. He is outside this page's three-way scope, but a reader taking the closing line at face value would conclude the skills convergence is uncontested. It is not; see skills-as-memory.

Content below is preserved as the 2026-07-16 state. Recommended refresh: extend to four lenses, or add Thorsten as an explicit dissent column.

Summary

Three speakers describe the same underlying change — models now improve faster than people can, and the durable advantage has moved from the model to the system you wrap around it — but from three non-overlapping vantage points:

theo-browne — strategy / psychology (what to build, how big to think)
konstantin — engineering / R&D (how the machinery works)
allie-miller — individual productivity / business (how a person operationalizes it daily)

They agree on the destination and disagree mostly on altitude, not direction.

At a glance

	theo-browne	konstantin	allie-miller
Source	2026-07-14-everything-we-knew-about-software-has-changed	2026-07-14-skills-based-on-git	2026-07-14-gap-between-ai-users-irreversible
Lens	Founder / educator	Model-builder (Sber/GigaChat)	Ex-Amazon AI leader / advisor
Audience	Engineers & founders	Agent developers	Knowledge workers, non-programmers
Core unit	Ambition / scope	The harness + git repo + agentic-loops	The personal-ai-operating-system
One-line thesis	think-wider-not-bigger — scope to the new model	Skills+data in git = agent memory	Build the OS once; models slot in
Faces toward	The market (what to build)	The machine (architecture)	The individual (adoption + judgment)
On code	code-as-throwaway, cost → 0	Commoditized; orchestration is what matters	Barely about code at all
Time posture	Present shock ("already changed")	Roadmap (tools→MCP→skills→loops; 2027)	Urgency ("irreversible in 12 months")

What they have in common

The bottleneck moved from the model to the human's system. Theo frames "models aren't useful for me" as a scoping problem on the human side; Konstantin's human evolves prompt-engineer → context-engineer → harness/loop-builder; Allie says winners and losers differ in mindset and taste, not expertise. None of them treats raw model capability as the constraint.
Markdown / skills as the atomic unit. All three independently converge on plain markdown as the durable building block — Theo's "G-brain tier" (a markdown file as an executable service on a cron), Konstantin's SKILL.md+ data in git, Allie's skills as "just folders with markdown." This is the vault's strongest cross-source thread — see skills-as-memory.
Infrastructure compounds; one-off prompting doesn't. Allie: build foundation docs once and every release "slots into a system you already understand." Konstantin: the git repo + auto-improvement compound over time. Theo: build for breadth/shape so others extend you (the Slack effect). Same instinct — invest in a reusable substrate, not individual prompts.
You only capture a new model's gains if the system is ready to absorb it. Theo: "push scope to match it." Konstantin: keep the harness constant and swap the LLM underneath. Allie: the new model "slots in." Identical mechanic, three vocabularies.
context-as-scarce-resource. Explicit in Konstantin ("smart zone," two-stage skill loading) and Allie ("context engineering, not prompt engineering"); implicit in Theo's orchestration era.
claude-code is the shared reference harness across all three.

Where they differ

Altitude / question answered

Theo → "what should I build, and how big?" Strategy and psychology. His deliverable is a mindset: shed developer-identity baggage (decoupling-identity-from-profession), treat code as disposable, pick embarrassingly ambitious ideas.
Konstantin → "how does the machinery actually work?" The deepest technical account: harness definition, tools → MCP → skills (evolution-of-agent-tooling), two-stage loading, CI as back-pressure, pruning windows, inner/outer/meta agentic-loops, demonstrated auto-improvement (GigaChat 1/89 → 11/89 over a weekend).
Allie → "how do I, a person, run this day to day?" Adoption mechanics: 3 foundation docs, 4 Claude surfaces, "just complain," proactive scheduled workflows, trust calibration, team-vs-headcount choices.

Framing of the same skills idea (Konstantin ↔ Allie overlap, noted in skills-as-memory)

Konstantin gives the engineering framing: git, CI/CD, merge-conflict resolution by models, storage ceilings, back-pressure loops.
Allie gives the business framing: folders you can hand to a teammate, compose, "share between agents," portable across ChatGPT/Perplexity/Gemini.
Theo mostly doesn't discuss skills at all — his nearest equivalent is markdown-as-service (the G-brain tier), the same "executable prose" instinct one layer out.

On code and craft

Theo: code is throwaway, cost heading to zero (code-as-throwaway); no guilt discarding work.
Konstantin: code/tools are commoditized; value is in orchestration and the accumulated skill/data repo.
Allie: code is largely absent — her audience is non-programmers, and her unit of value is context + workflows, not source.

Learning / self-improvement

Konstantin demonstrates it today via the git/skill loop (auto-created skills, weekend self-improvement runs).
Allie forecasts it as a coming shift — "self-learning models with real weight updates," explicitly distinguished from today's memory-file retrieval (Status: tentative).
Theo doesn't address learning loops; his axis is ambition, not memory.

Emotional register

Theo: present shock / identity ("everything we knew has changed"; the iOS-6 skeuomorphic phase).
Konstantin: calm evolutionary roadmap (each generation named, 2027 forecast).
Allie: urgency / FOMO ("the gap will be irreversible in 1 year").

Tensions worth noting (complementary, not contradictory)

Throw code away (Theo) vs persist everything in git (Konstantin). Reconciled by distinguishing the artifact from the capability: discard the throwaway code, but keep the skill + data that can regenerate it. Theo keeps the ambition; Konstantin keeps the memory.
Deskilling (Theo: code as throwaway) vs re-skilling (Allie: taste is the meta-skill). Both point at the same relocation of value — away from execution, toward judgment/framing.
None of the three directly contradicts another; the disagreements in this corpus are elsewhere (e.g. BYO- vs company-managed harness, online vs in-person networking — see overview).

Entities: theo-browne · konstantin · allie-miller
Sources: 2026-07-14-everything-we-knew-about-software-has-changed · 2026-07-14-skills-based-on-git · 2026-07-14-gap-between-ai-users-irreversible
Concepts: skills-as-memory · personal-ai-operating-system · harness · think-wider-not-bigger · context-as-scarce-resource · code-as-throwaway
Timeline: ai-agent-evolution
Overview synthesis: overview

Open Questions

Theo and Allie both gesture at markdown-as-the-unit but neither publishes a reusable template (foundation docs / a good SKILL.md) — Konstantin has the mechanics but no size/data standards. The three together still leave the starter template unresolved (webinar-relevant).
Does Theo's "throw it away" hold once Konstantin-style accumulated skills become the memory? I.e. is there a point where the repo is too valuable to reset — and does Konstantin's meta-loop (periodic wipe-and-restart) actually contradict "persist everything"?

8.8 KiB Raw Blame History Unescape Escape