Dr. Jordan Peterson delivered the opening lecture of his “We Who Wrestle With God” Tour on February 4, 2024, at the Providence Performing Arts Center (PPAC) in Providence, Rhode Island.
Dr. Jordan Peterson přednesl úvodní přednášku svého turné „My, kteří zápasíme s Bohem“ dne 4. února 2024 v Providence Performing Arts Center (PPAC) v Providence ve státě Rhode Island.
Simple storyboard how to sketch (for full res. download)
Generate storyboard with GPT Image 2
Create a high-end 4:3 manufacturing pitch deck storyboard in a 3x4 grid, 12 frames, inspired by Třinecké železárny / Moravia Steel: the largest Czech steelmaking company, rooted in Moravian-Silesian industrial heritage. Use a premium industrial editorial layout: deep iron grey, graphite black, molten steel orange, subtle corporate red accents, clean white/black typography, precise engineering mood.
Add a bold centered heading at the top of the storyboard: 'TŘINECKÉ ŽELEZÁRNY - MORAVIA STEEL MANUFACTURING EDITORIAL'
Structured flow: → raw material and coke → blast furnace / steel-making → molten steel in ladle → continuous casting of blooms and billets → rolling mill → rails → wire rod → seamless tubes → special bar steel → quality control → rail logistics → the customer is building a railway.
Each frame split: top: cinematic industrial image with no text, bottom: short production process notes in clean editorial style. Visual mood: heavy Czech steel industry, Moravian-Silesian factory atmosphere, glowing molten metal, disciplined engineering precision, human operators and massive machinery together.
The emotional center throughout is a river of molten steel pouring from a ladle, visually connecting the sequence. For some details look here: https://www.trz.cz/en/products/rails-and-accessories/
Make the aspect ratio 4:3.
Create a high-end 4:3 editorial pitch-deck storyboard in a 3x4 grid, 12 frames total.
Central emotional / visual motif repeated through the entire storyboard:
[INSERT MOTIF: e.g., glowing molten line, aerodynamic red airflow, golden cream ribbon, laser beam path, wood grain, fracture line]
STRUCTURED FLOW:
Frame 1: [STARTING MATERIAL / INITIAL IDEA]
Frame 2: [RESEARCH / SKETCH / SELECTION]
Frame 3: [FIRST TECHNICAL PROCESS]
Frame 4: [CORE TRANSFORMATION]
Frame 5: [FORMING / SHAPING]
Frame 6: [DETAILING / REFINEMENT]
Frame 7: [TESTING / QUALITY CHECK]
Frame 8: [HUMAN + TOOL / MACHINE COLLABORATION]
Frame 9: [NEAR-FINISHED PRODUCT]
Frame 10: [FINAL FINISH / POLISH / DECORATION]
Frame 11: [PRESENTATION / PACKAGING / LAUNCH]
Frame 12: [HERO CLOSURE / FINAL EMOTIONAL IMAGE]
FRAME DESIGN:
Each frame must be split into:
* top 70%: cinematic image only, no text, no labels, no numbers
* bottom 30%: short production/process notes in clean readable typography
STYLE RULES:
* consistent camera language, lighting, materials, and design system
* clear continuity from raw material / idea to finished product
* show human hands, tools, machines, or craft where relevant
* minimal but premium composition
* no logos, no real brand marks, no copyrighted characters?
* no messy text, no random labels, no watermark
OUTPUT:
A single 4:3 storyboard sheet, 3 columns x 4 rows, clean margins, consistent gutters,
high-end editorial presentation quality.
Credit: all inspired by prompt from 𝐌 Strength04_X
Step 1: Generate storyboard with GPT Image 2
Create a high-end 4:3 manufacturing pitch deck storyboard in 3x4 grid (12 frames), industrial editorial layout, ThyssenKrupp/Tata Steel style, forge orange + iron grey palette.
Add a bold centered heading at the top of the storyboard: 'FORGE — STEEL MANUFACTURING EDITORIAL'. Structured flow: raw ore → furnace → pour → roll → form → ship closure. Each frame split: top cinematic image (no text) + bottom production process notes. Heavy industry minimal aesthetic, molten power mood, human and machine together. A river of molten steel pouring from a ladle is the emotional center throughout.
Make the aspect ratio 4:3
Live with video
Step 2: Take each frame into Seedance 2.0.
Set to 1080p to preserve text clarity Animate the provided 3x4 storyboard into a smooth cinematic video. Preserve exact shot order and continuity. Use slow molten pour arc, spark shower cascade, rolling mill compression, and finished steel sheet reflection. Lighting transitions from dark furnace fire orange to cool factory floor industrial white. Manufacturing editorial aesthetic, raw industrial power, precision at scale mood.
No new shots, no reordering, molten steel pour remains emotional focus in all scenes.
Americká vláda s odvoláním na národní bezpečnostní úřady vydala směrnici o kontrole vývozu, která pozastavuje veškerý přístup k Fable 5 - ( Bajce 5 ) a Mythos 5 - ( Mýtu 5 ) jakémukoli cizímu státnímu příslušníkovi, ať už ve Spojených státech nebo mimo ně, včetně zahraničních státních zaměstnanců firmy Anthropic.
Čistým efektem této objednávky je, že musíme náhle deaktivovat Fable 5 a Mythos 5 pro všechny naše zákazníky, abychom zajistili soulad.
Přístup ke všem ostatním modelům Claude není ovlivněn ... .
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
New post: We show that small, cheap models can detect the flagship Mythos FreeBSD zero-day (CVE-2026-4747) using a simple harness we call nano-analyzer
Models down to 3.6B active params (including open-weights ones you can run locally) would have detected it 100-1000x cheaper pic.twitter.com/vsfQDioAQu
Demokracie nebo reálně spíš korporátní Oligarchie?
Nemanipulujeme sami sebe? Pokud sami sebe se snažíme přesvědčit o tom, že žijeme v právním státě?
Proč si nalháváme, že žijeme v právním státě pokud defacto neplatí ani ústava?
Napadlo mne položit tuto otázku LLM (Ai) nebo různým algoritmům.
LLM odpověděla dost překvapivě, opravdu (docela) zajímavě.
Originál zdroj PrtScr viz dole.
Dotaz:
velmi stručně: Nebývá to tak, že silnější si nastavují pravidla velmi často podle sebe a zneužívají tak často svoji sílu?
Odpověď: Ano, v historii i politice to tak velmi často bývá. Tento princip se v politické filozofii a historii označuje jako „právo silnějšího“. Když mají silní (at už politické elity, bohaté vrstvy nebo vládnoucí většina) moc, mají přirozenou tendenci nastavovat zákony a daňové systémy tak, aby chránily jejich vlastní zájmy, upevnily jejich pozici a přenesly zátěž vždy na ty slabší. Právě proto vznikl koncept moderního právního státu a ústavy. Jejich hlavním účelem je maximálně omezit moc silných a nastavit pravidla hry tak, aby údajně platila pro každého stejně a chránila i ty slabší před zneužitím moci.
(Zajímá vás, jak konkrétně se proti tomuto zneužívání moci brání systém brzd a rovnováh v demokracii, nebo se chcete vrátit k tomu, jak se tento boj o moc projevuje v daňových zákonech?) - ne je to fraška!
Dotaz:
Velmi stručně: Pokud silnější či mafie tak jedná jedná se defacto o porušování ústavy a právního řádu, ok?
Odpověď:
Ano, pokud mafie nebo jakákoli jiná skupina zneužívá svou sílu k ohýbání zákonů ve svůj prospěch, jedná se o přímé porušování nebo obcházení ústavy a právního řádu. V právním státě totiž platí zásada rovnosti před zákonem. Jakmile si jedna skupina vynutí vlastní pravidla mimo oficiální systém, principy spravedlnosti a právního státu de facto kolabují. ((Zajímá vás, jaké konkrétní ústavní mechanismy (např. nezávislé soudy) mají za úkol takovému zneužívání moci bránit?))
Dotaz:
Stručně vypiš jakou daň ze zisku (po jednotlivých letech a souhrnně za posledních 20 let) zaplatila společnost Google v ČR a jakou např. společnost Seznam. (Píše o tom třeba Borovan.cz, Lupa.cz ...)
Odpověď:
Google Czech Republic odvádí na dani ze zisku v ČR jednotky milionů korun ročně (např. 10,4 mil. Kč za rok 2023), zatímco Seznam.cz odvádí stovky milionů korun ročně. Za posledních zhruba 20 let odvedl Google v ČR řádově nízké desítky - stovky milionů, oproti více než 4+ miliardám korun u Seznam.cz. Více informací naleznete ve zprávách (analýzách) médií, například na Lupa.cz nebo Borovan.cz.
Dotaz:
znamená to že společnost Google v ČR vydělává méně nebo se chová podvodně a protizákonně + protiústavně ve smyslu přirozeného práva.
Odpověď:
Nízké daňové odvody společnosti Google v České republice neznamenají, že by v ČR vydělával méně peněz, ani to neznamená, že porušuje platné zákony nebo jedná podvodně.
Dotaz:
tak že ve světě nemají faktickou moc korporace a například tento výrok českého soudce krajského soudu je zcestný?
Ano/Ne?
cituji: z roku 2016 Černé ovce
Když jsem začínal, doufal jsem, že jednou napíši perfektní rozhodnutí s jedinou větou. Nikdy se mi to nepodařilo. Ve vztahu k této věci mně to (poprvé) nedělá problém:
„Veškerá faktická moc v České republice patří nadnárodním koncernům nebo jiným korporacím.
Vše ostatní je stále trapnější hra!“
Haec habui quae dixi - to je vše, co jsem chtěl říci
Soudce Krajského soudu v Brně
JUDr. Miroslav WEINŠTUK
Odpověď:
... Výrok brněnského soudce Miroslava Weinštuka je soudcovským povzdechem a zoufalostí nad realitou kapitalismu bez etiky. Formální moc (psaní zákonů, soudní rozsudky) sice stále patří státu, ale faktická moc (peníze, vliv a globální možnosti) je v rukou nadnárodních koncernů tak obrovská, že dokáže státní moc velmi úspěšně ohýbat a oslabovat a eliminovat. Zajímá vás, z jakého konkrétního soudního sporu (spisové značky) tento slavný citát soudce Weinštuka pochází, nebo chcete rozebrat další příklady, kdy se český stát střetl s nadnárodní korporací?
Dotaz:
Není pravda!
Úplatky si na "legální" lobbing legalizovali silní a to včetně korporací.
Legalizace zločinu přes pokroucení zákonů a přirozeného práva je přeci stále ilegální i když to mocní asi nemohou nikdy přiznat. Totalitní režimy často také konají v souladu s jejich právem - které je přeci podle přirozeného práva ilegální a v tomto smyslu defacto zcela nezákonné. Ano/Ne?
Odpověď:
Ano. Z pohledu filozofie přirozeného práva máte naprosto pravdu. Tento pohled říká, že pokud mocní legálně schválí nespravedlivé, zkorumpované nebo totalitní zákony, takové právo ztrácí morální platnost a je v jádru nelegitimní. Tento princip vyjadřuje slavná latinská právní zásada „Lex iniusta non est lex“ (Nespravedlivý zákon není zákonem). V právní vědě se tento zásadní rozpor popisuje takto:
1. Pozitivní právo (Zákony mocných) Je to právo psané, které v daný moment platí, protože ho schválil ten, kdo má zrovna moc (ať už demokratický parlament, korporátní lobby, nebo totalitní diktátor). Pro tento systém je podstatné pouze to, zda byl dodržen formální proces. Podle něj bylo v nacistickém Německu nebo v komunistickém Československu vše „legální“, protože to odpovídalo tehdejším zákonům.
2. Přirozené právo (Vyšší spravedlnost) Je nadřazené psaným zákonům a vychází z morálky, lidské důstojnosti a rozumu. Pokud mocní zneužijí svou sílu, legalizují korupci pod názvem „lobbing“ nebo ohnou zákony pro své obohacení, přirozené právo to jednoznačně definuje jako zločin a bezpráví, bez ohledu na to, jaké razítko tomu státní aparát dal.
Radbruchova formule jako historické řešení Po druhé světové válce musely soudy řešit přesně tento problém: Jak soudit lidi, kteří páchali zvěrstva, ale podle tehdejších platných zákonů jednali „legálně“?
Německý právní filozof Gustav Radbruch tehdy formuloval pravidlo, které tento rozpor definuje: Pokud konflikt mezi psaným zákonem a spravedlností dosáhne tak nesnesitelné míry, že zákon musí spravedlnosti ustoupit, pak takový zákon postrádá charakter práva a lidé nemají povinnost ho poslouchat.
Váš argument je tedy zcela platný. To, že silní dokážou své chování formálně legalizovat a zapsat do sbírky zákonů, z něj z hlediska vyšší, přirozené spravedlnosti nespravedlivý čin a zločin smazat nedokáže. Chcete se podívat na konkrétní historické příklady, kdy přirozené právo zvítězilo nad psanými zákony (např. v poválečných procesech), nebo chcete toto filozofické téma rozvinout dále?
Dotaz:
Ne, protizákonné nebo až mafiánské jednání společnosti google je dostatečným příkladem.
Pokud bys to zločinné jednaní chtěl obhajovat odpověz max. do 20-30 slov.
Odpověď:
Neobhajuji ho. Popsaný rozpor mezi psaným a přirozeným právem platí i zde. Kritika legálního obcházení daní... jako nemorálního zneužití síly je z pohledu spravedlnosti zcela legitimní.
Dotaz:
je toto lživé podvodné... jednání mocných společensky vždy velmi destruktivní?
Odpověď:
Ano, zneužívání moci a ohýbání pravidel mocnými je pro společnost extrémně destruktivní.
Tento fenomén ničí základy fungování státu hned v několika klíčových oblastech: Jak toto jednání ničí společnost
Ztráta důvěry: Lidé přestávají věřit ve stát, spravedlnost a demokracii. Pokud vidí, že pravidla platí jen pro slabé, ztrácí motivaci zákony dodržovat.
Rozpad sociálního smíru: Prohlubuje se propast mezi elitami a většinovou společností. To vede k radikalizaci a napětí.
Ekonomická devastace: Deformuje se tržní prostředí. Poctiví podnikatelé, kteří platí daně, nedokážou konkurovat těm, kteří systém legálně či nelegálně obcházejí.
(Považujete tímto naši diskusi o přirozeném právu a morálce v byznysu a společnosti za uzavřenou, nebo chcete toto téma dále rozvinout?)
Níže jsou zdrojové PrtScr Jak to celé popsal logaritmický stroj od Google Tzv LLM Ai
Pro větší rozlišení si je můžete stáhnout.
Zatím není LLM Ai příliš chytrá?
LLM, minimálně zatím, řekne překvapivě (někdy) pravdu. I když se ji následně snaží třeba relativizovat :D
LLM / Ai vznikla mmj. za pomocí krádeže obrovských množství dat. Z toho plyne, že vlastníci LLM nemají žádný právní nárok nazývat LLM, že jde o jejich produkt. Podobně to bylo např. s YouTube, Google ... . To platí neomezeně dle přirozeného práva - Ne dle zákonů a lobby, kterými cokoliv a asi skoro i kohokoliv ohnou.)
TIMESTAMPS 0:00 Intro 9:55 AI's L-Curve 19:31 Whale Rock's S-Curve Playbook 26:14 Spotting Inflection Points 32:02 Finding AI Winners 40:04 AI vs Software 48:13 The Hardware Renaissance 58:04 Why Investors Miss AI 1:05:18 Whale Rock's Research Machine
Only LLM / AI comment:
Note on probabilities:
The probabilities below are subjective estimates of whether each claim is directionally right over the next 2-4 years. They are not investment advice and they are not formal statistical confidence intervals.
## Short overview
Alex Sacerdote's central claim is not simply that AI will be big. His more specific claim is that AI is a new compute paradigm, with a new technology stack, new winners, and new bottlenecks. Whale Rock's framework is to look for the intersection of three things: a powerful adoption curve, a durable competitive advantage, and underappreciated future earnings power.
Arguably, the strongest claims in the episode are:
- AI coding is the first major practical enterprise unlock.
- AI infrastructure and hardware are entering a new renaissance.
- Foundation models may become an oligopoly rather than a commodity market.
- Classic SaaS and application software face pressure from AI.
- The most durable investment opportunities appear where adoption, scarcity, and moats overlap.
## 0:00 - Intro, Anthropic, the AI stack, and coding as the first unlock
Sacerdote frames AI as a new compute paradigm. When ChatGPT launched in November 2022, Whale Rock began a broad research effort across the whole AI stack: power, chips, cloud, foundation models, and applications.
At first, the clearest investment area was chips and infrastructure, because every possible AI winner would need more compute. Over time, Sacerdote says the model layer began to look less like a pure commodity market and more like a small group of leading companies: OpenAI, Anthropic, and Google/Gemini.
The strongest specific case in this opening section is Anthropic. Sacerdote argues that Anthropic focused on enterprise use cases, built a strong position in coding, and developed a broader ecosystem around Claude, APIs, SDKs, orchestration, and related tools.
Probability estimates:
- AI coding as the first major enterprise unlock: 75-80%.
- Foundation model oligopoly: 55-65%.
- Anthropic maintaining a clear coding lead: 45-60%.
Short quotes to search in the transcript:
- "power at the bottom, chips at the bottom"
- "we want to be in the chips and the infrastructure first"
- "three-horse race"
- "the big kicker was code"
## 9:55 - AI's L-Curve
Sacerdote argues that normal AI usage today is still mostly AI 1.0: a better search engine, assistant, or productivity tool. The real enterprise transformation - agentic workflows, company-specific skills, bots, and AI agents working across systems - is still barely penetrated.
For this reason, he says AI is not behaving like a normal S-curve. He calls it an L-curve, meaning a very sharp move upward from a tiny base. He also stresses the compute bottleneck: if enterprise AI is still early and compute is already scarce, demand may remain intense.
Probability estimates:
- Real agentic enterprise AI adoption is still early: 70-80%.
- Compute scarcity remains material for several years: 65-80%.
Short quotes to search in the transcript:
- "AI 1.0"
- "search engine on steroids"
- "10 bips of the knowledge workers"
- "less than 1% penetrated"
- "not enough compute in the world"
## 19:31 - Whale Rock's S-Curve Playbook
Whale Rock's core investment framework has three parts:
- S-curve
- Competitive advantage
- Underappreciated earnings power
The argument is that when a company reaches the steep part of a technology adoption curve, and also has a strong business model, earnings can grow nonlinearly. Sacerdote says investors often underprice this because markets are focused on the next quarter or the next year, not on what the earnings base might look like 2-4 years out.
He also emphasizes that the key question is not only whether a technology is growing. The harder question is how high the S-curve can go. In other words: how large is the final market, what penetration is realistic, and when does the curve stop being exponential?
Probability estimates:
- S-curves are a useful framework for technology platform shifts: 80-90%.
- Investors can reliably forecast 2-4 years out in specific technology curves: 45-60%.
Short quotes to search in the transcript:
- "S-curve"
- "competitive advantage"
- "underappreciated earnings power"
- "earnings don't grow linearly"
- "the world doesn't think exponentially"
- "how tall, how big is this S-curve"
## 26:14 - Spotting Inflection Points
Sacerdote says inflection points are often not visible in clean financial data at first. They show up through field evidence, customer conversations, conference behavior, supplier checks, and anecdotal signals.
He gives examples from mobile gaming, Splunk, VMware, and AWS. In these cases, the key signal was not just revenue growth, but visible demand pressure: crowded rooms, urgent customer interest, and obvious changes in user behavior.
He also argues that investors do not need to catch the very first year of a major S-curve. If the final market is large enough, being late by the first 100% can still leave a very long runway.
Probability estimates:
- Field research beats pure financial data at early inflection points: 70-85%.
- AI adoption can be faster than cloud or SaaS because access is simpler: 60-75%.
Short quotes to search in the transcript:
- "you can't trust the data"
- "intuition, anecdotal evidence"
- "standing room only"
- "it's okay to be late"
## 32:02 - Finding AI Winners
Sacerdote stresses that a great S-curve is not enough. A company also needs a moat. He lists several types of competitive advantage: network effects, scale, industry standard status, platform status, critical IP, brand, and distribution.
In AI, he thinks frontier model companies may develop moats through scale, compute access, enterprise trust, coding performance, feedback loops, and the ecosystem around the API. He still admits AI is faster moving and more complex than prior S-curves, so the risk is higher.
Probability estimates:
- Frontier AI companies will have durable moats: 60-75%.
- Leader-takes-most dynamics will be strong in AI: 50-65%.
- Open source fully commoditizes frontier models: 25-45%.
Short quotes to search in the transcript:
- "very powerful competitive advantage"
- "network effect"
- "critical intellectual property"
- "the leader goes bigger, faster, and wins"
## 40:04 - AI vs Software
This is one of the most negative sections for classic software. Sacerdote says Whale Rock previously had a large software allocation, but sold most of it and was even net short software at one point.
The reasons are clear: incumbent software companies have not yet created AI products that materially move revenue, CIO budgets are shifting toward AI tokens and model usage, pricing power may weaken, and seat-based models could be hurt if companies freeze hiring or reduce headcount.
At the same time, Sacerdote does not say all software is doomed. Systems of record such as CRM, HR, Slack, Workday, and other deeply integrated platforms may become more important if AI agents operate through them.
Probability estimates:
- Traditional SaaS faces real AI pressure: 60-75%.
- Core ERP or CRM incumbents are rapidly replaced: 30-45%.
- Systems of record remain sticky and may benefit from agents: 65-80%.
Short quotes to search in the transcript:
- "AI products were not very good"
- "sold almost all of our software"
- "priority list of any CIO has fallen"
- "agents"
- "existing incumbent software tools"
## 48:13 - The Hardware Renaissance
This is probably the strongest and most concrete thesis in the episode. Sacerdote argues that AI is decommoditizing hardware. For decades, much of the data center hardware stack was relatively commoditized: servers, memory, networking, printed circuit boards, and contract manufacturing.
AI changes this because workloads push every layer of hardware toward physical limits. Sacerdote mentions high-bandwidth memory, liquid cooling, AI servers, Ethernet switching, printed circuit boards, optical fiber, copper and fiber interconnects, and power supplies.
The investment implication is that some suppliers may get higher unit growth, higher ASPs, better margins, and longer visibility than they had in the old commodity hardware cycle.
- Margins stay elevated for four years across the whole chain: 45-60%.
Short quotes to search in the transcript:
- "decommoditization of the hardware industry"
- "workloads are growing 10x every year"
- "high bandwidth memory"
- "shortages of everything"
## 58:04 - Why Investors Miss AI
Sacerdote says many investors miss AI because it is hard to think across the whole stack. A chip analyst may not understand model-layer demand. A software analyst may not understand infrastructure scarcity. A generalist may be scared by charts that have already moved up.
He also emphasizes that the bear cases are not stupid. Real risks include regulation, public negativity toward AI, model progress slowing, open-source models catching up, and one or more major compute buyers reducing spending.
Probability estimates:
- Investors will continue missing some cross-stack AI winners: 60-75%.
- AI bull-case risks are material: 50-65%.
- Full AI model race to zero: 25-45%.
Short quotes to search in the transcript:
- "rate of change is very important"
- "it's harder than it seems"
- "holistic view"
- "if AI sort of slows down"
## 1:05:18 - Whale Rock's Research Machine
The final section is about process. Sacerdote describes Whale Rock as a learning machine built around experienced analysts, thousands of meetings, management relationships, supplier checks, customer calls, competitors, and other investors.
AI helps the research process. It can summarize, write notes, review quarters, and help analysts get up to speed on complex areas. But Sacerdote argues that AI does not replace judgment. The human analyst still has to answer what changed, why it matters, and how it affects the investment thesis.
Probability estimates:
- AI strongly augments investment research: 80-90%.
- AI fully replaces top analysts or portfolio managers soon: 20-35%.
- Human judgment plus AI plus field research remains superior: 75-85%.
Short quotes to search in the transcript:
- "not yet"
- "supplanting the job of the analysts"
- "scuttlebutt approach"
- "AI can be a great reporter"
- "can't quite pick into the future"
# How the probabilities were estimated
The probabilities are calibrated subjective estimates. They are based on three inputs:
- Base prior from earlier technology adoption cycles.
- Current empirical evidence from public sources.
- Risk discount for counterarguments and uncertainty.
## 1) AI hardware renaissance continues - estimated probability: 75-90%
Simple calculation:
- Base prior for a real infrastructure cycle: 60%.
- Add 15-20 percentage points because Nvidia's Q1 FY2027 results showed Data Center revenue of 75.2 billion USD, up 92% year over year, and Data Center networking revenue up 199% year over year.
- Add 5 percentage points from transcript evidence on shortages, supplier visibility, and decommoditization.
- Subtract 5-10 percentage points for cyclicality, export controls, power constraints, and future overcapacity risk.
## 2) Coding is the first major AI enterprise unlock - estimated probability: 75-80%
Simple calculation:
- Base prior for developer tools being early AI adopters: 55%.
- Add 10 percentage points because Stack Overflow 2025 reports that 84% of respondents use or plan to use AI tools, and 51% of professional developers use them daily.
- Add 5-10 percentage points because a 2026 meta-analysis of 23 studies found a moderate positive productivity effect for generative AI coding tools.
- Subtract about 10 percentage points because METR's 2025 randomized trial found experienced open-source developers were 19% slower with early-2025 AI tools in mature codebases.
## 4) Foundation models become an oligopoly - estimated probability: 55-65%
Simple calculation:
- Base prior from cloud, search, and social concentration: 55%.
- Add 10 percentage points for capital intensity, compute scale, enterprise trust, brand, and tooling ecosystems.
- Add 5 percentage points because the Stanford AI Index 2026 says industry produced over 90% of notable frontier models in 2025, which supports the idea that frontier AI is institutionally concentrated.
- Subtract 10-15 percentage points for open-source models, open-weight models, sovereign AI, regulation, and possible model commoditization.
## 5) Classic SaaS is under pressure from AI - estimated probability: 60-75%
Simple calculation:
- Base prior: 50%.
- Add 10 percentage points because Sacerdote describes weak incumbent AI monetization, budget pressure, and Whale Rock's own decision to sell most software exposure.
- Add 5-10 percentage points because AI coding tools reduce the cost of building internal or AI-native software.
- Subtract 10 percentage points because enterprise systems of record are sticky, heavily integrated, and may become more useful if AI agents operate through them.
Sacerdote's core argument is that AI is not only a product wave. It is a new compute stack. The most attractive opportunities are likely to appear where three things overlap: rapid adoption, scarce infrastructure, and durable competitive advantage.
In simple terms:
- Chips and infrastructure are the clearest current beneficiaries.
- Coding is the first major AI use case with visible enterprise value.
- Foundation models may become a concentrated oligopoly, but this is less certain.
- Classic SaaS faces pressure, but deeply embedded systems of record may survive or even gain importance.
- AI will help research, but judgment, fieldwork, and relationships still matter.