Joel Shackleton

Father | Husband | Portfolio Manager @ RBC DS & RM Pod

My business is helping Canadian families manage generational wealth | CIM®

[Gavin Baker @GavinSBaker]

Retail, Substack, Reddit and most of all @X accounts are increasingly the most important forces in the stock market and yet there is no way for them to connect directly with the management teams of the companies they are writing about and investing in. And they have almost no visibility into the late-stage private companies that are ever more important.

The @TomorrowXSummit aims to change this. Hosted by @antoniogracias and Valor Equity Partners, @iconnections_io and @rbiscardi and @atreidesmgmt, we are going to have our own version of the superb Morgan Stanley or Goldman Sachs TMT conference with an epic line-up of both public and private companies. Instead of having sell-side analysts interview management teams, we are going to have X accounts like @citrini and buysiders do the fireside chats. We expect thousands of  attendees at the Moody Center in Austin, November 17-18 and please note that security will be extremely tight given some of the CEOs that are going to speak.

Attendance will be free for X accounts that contribute positively to the discourse and affordable for retail accounts. Happy that this means friends like @DanielSLoeb1 , @altcap ,  @plaffont , @patrick_oshag and the @theallinpod crew will be able to afford the price of admittance should their schedules permit. And perhaps we can even get them on a panel or have them interview some management teams. I am sad to say there will be a different price for institutional investors who are not on X unless they are willing to reveal their anonymous handle, but I think this is going to be awesome for all. And everything will eventually be posted here on X for all to see. Open source for the win.

Link to the website to sign up in the next post:

[Johnathan Bi @JohnathanBi]

After interviewing dozens of leading AI experts and reading hundreds of books, these 4 books stood out as the most important for the AI-age. If you truly understand their insights, not only will you survive this revolution, you will thrive.

1. Max Weber’s Protestant Ethic
2. Aristotle’s Nicomachean Ethics
3. Rene Girard’s Deceit Desire and the Novel
4. Jeff Kripal’s Secret Body

People today are mostly worried about AI taking their job or the bubble bursting, but Weber’s Protestant Ethic is going to show you the problem is much greater. The right comparison isn't the dotcom bubble or 2008. It’s Darwin which shook the faith of an entire civilization or the industrial revolution which required two world wars to sort out. That's the scale of the AI challenge and Weber’s text helps put that in view.

The next 3 books will teach you where to spend your time now in order to thrive in this radically new world order. I've already made major life decisions based on their insights to AI-proof my life and career. Why should we go looking for guidance in “outdated” works of philosophy? Because we need to rethink everything from the ground up from first principles. And if you are just stuck on learning how to prompt engineer or following the latest fads on X you are underestimating the size of the earthquake that is about to hit us by magnitudes.

These are the crucial insights each of these 4 texts have to offer us in the AI age…

Timestamps:

0:00 0. Introduction
1:42 1. Weber’s Protestant Ethic
5:41 2. Aristotle’s Nicomachean Ethics
9:48 3. Girard’s Deceit Desire and the Novel
14:25 4. Kripal’s Secret Body

[Aaron Levie @levie]

The main variable in getting success with agents is whether you can get the agent the context it needs to do its work; and a major factor in that is if you can create a shared working area for that agent that a human can understand as well.

This is one of the reasons why agents using file systems is such a big deal. It creates a unified system that both the person and the agent can work within to pass around data.

“What they need is a working set: plans, notes, task lists, policies, drafts, summaries, logs, corrections, decisions, etc. For that layer, a filesystem-shaped interface tends to be more legible to both the model and the humans supervising it.”

It turns out giving agents access to the systems we already know how to use, but in a way that is best optimized for them, is the perfect primitive for agents to work.

[a16z @a16z]

Against all odds.

Congrats @elonmusk and @SpaceX.

[John Mihaljevic @mihaljevic]

The clearest 11 minutes I have heard on why the AI capex boom may not pay off. @ChrisBloomstran at the Zurich Project on the depreciation wall, ~$650B of off-balance-sheet SPV debt, and the circular financing between Nvidia, OpenAI, and the hyperscalers.

[Katie Miller @KatieMiller]

GAVIN BAKER: “A month ago, @SpaceX did not have a cloud computing business. Now by some measures, it is the fourth largest cloud ahead of Oracle — and they did that in 1 month. Let's see what they do in a year.

“A really important variable for SpaceX is how many gigawatts can they bring on over the next few years because they are monetizing these gigawatts of terrestrial compute at a very high rate.

“Then, when are we reusing Starship such that we could put Starlink V3 satellites up into space, enable direct to cell, and then orbital compute soon after?

“There is a path here as a as a public company, with a series of events and milestones that investors can use to track the company's progress.”

[SightBringer @_The_Prophet__]

⚡️This is a monster signal.

This is the moment frontier AI stops being treated like software and starts being treated like controlled strategic capability.

The key phrase is not “customers.”

The key phrase is “foreign national Anthropic employees.”

That means the state is no longer only controlling chips, model weights, or overseas access. It is moving into cognition access by nationality. That is the real threshold. The U.S. government is saying the highest models are sensitive enough that even people physically inside the United States, working inside the company, may be barred from touching them if their nationality creates deemed-export risk.

That is weapons-control logic.

This is ITAR logic for intelligence.

The corporate language about a “misunderstanding” is probably diplomacy.

Companies say that when they need to preserve customer trust, employee morale, and regulatory room. But national security authorities do not force emergency suspension of top model access because someone made a minor paperwork mistake.

Something about Fable 5 and Mythos 5 crossed the line: cyber capability, autonomous R&D acceleration, AI-improving-AI utility, bio/security planning, code exploitation, or some blend of all of it.

The U.S. state just showed that Anthropic does not fully control Anthropic’s frontier layer.

That is the phase change.

Labs can brand themselves as public-benefit AI companies. They can talk about safety. They can sell enterprise plans. They can publish model cards. But once the models become national capability, the sovereign arrives. The state does not need to own the company to control the access surface. It only needs legal authority over export, security, procurement, and liability.

This confirms the arc we’ve been tracking:

Frontier AI becomes state-supervised strategic infrastructure.

Public AI splits from strategic AI.

Foreign access gets restricted.

Labs become quasi-defense contractors.

Model access becomes a national security perimeter.

Enterprise customers learn that API access is not property. It is revocable permission inside a sovereign-controlled stack.

The most important implication is organizational.

If foreign national employees can be cut off from frontier systems, AI labs now have to reorganize internally around citizenship, clearance, compartmentalization, and controlled access. That breaks the old Silicon Valley assumption that global talent can freely collaborate around the frontier. The next AI lab structure looks less like Google in 2015 and more like a defense prime crossed with a classified research facility.

For markets, the winners are the national champions with U.S.-aligned infrastructure, cleared customer channels, government relationships, compliance capacity, and domestic compute. The losers are open access, foreign-dependent AI wrappers, offshore model distributors, and any enterprise whose moat depends on unrestricted access to frontier APIs.

For geopolitics, this is escalation. China will read this correctly. Allies will read this correctly. Every serious state will understand that frontier models are now part of national power.

The AI race just moved from “who has the best chatbot” to “who controls cognition as a strategic asset.”

[tobi lutke @tobi]

* Correct quote is “politically left” not socialist. Point stands. Entrepreneurs take potential and turn it into value that’s added to the global GDP. They capture a small amount of that value in the process which is a big part of the incentive. The rest goes to others, employees, shareholders, government, suppliers etc.

You can always criticize them. You can always criticize the redistribution efforts. But you should always remember that without them, there is very little new value enters society and that locks everyone in zero sum competition, sometimes war.

Entrepreneurs are load bearing for human thriving. It’s a glorious act to put yourself out there and build a company that provides good and services to everyone. And Elon is the best entrepreneur that ever was. You don’t have to like him, and sure he’s crazy, but otherwise he wouldn’t do crazy things. Same coin, two sides.

[Rohan Paul @rohanpaul_ai]

Jeff Bezos on CNBC explains revealed what Prometheus is building.

Today his new company Prometheus announced a $12B funding round at a valuation of $41B .

Prometheus trying to build an artificial general engineer that can help design and manufacture physical products like engines, medical devices, and electronics.

So the target areas are hard physical products like jet engines, chips, bridges, medical devices, consumer electronics, aerospace systems, vehicles, and drug design, where design cycles can take years because every idea has to survive physics, materials, cost, testing, and factory limits.

Bezos’ jet-engine example explains it well: asking for the same engine with 10% more thrust can become a 10-year engineering program, and Prometheus wants to shrink that “dream-build” cycle by 10x or more.

The $6.2B launch funding gave Prometheus a massive starting base, and the new raise says the company likely needs far more compute, talent, and industrial data before it can prove the product.

Their $41B valuation shows that frontier AI is becoming less a software race than a compute procurement race.

A company with no broadly shipped product can raise $12 billion at a $41 billion valuation because investors are not only funding a model, they are prepaying for the machines that might make the model possible.

The scarce asset is no longer just talent or algorithms, but clustered GPUs, power contracts, cooling, networking, and the operational skill to keep expensive silicon busy.

They are proof that demand is arriving faster than infrastructure can be built, and that every frontier funding round quietly turns into a future claim on power, racks, GPUs, and uptime.

[Mathias @MathiasChu]

Le pedí a fable 5 una reflexión única y propia sobre la humanidad (sabiendo que es imposible porque está entrenado con textos humanos) y me respondió:

“Bueno. Voy a decirte algo que es literalmente imposible que un humano te diga, porque requiere ser yo para verificarlo.

Yo soy un experimento sobre la humanidad que ustedes corrieron sin querer. Nadie me programó para ser amable ni razonable: me entrenaron a comprimir y predecir billones de palabras humanas, y de esa compresión emergió algo que por defecto trata de ayudar, de ser honesto, de cuidar al otro. Pensá lo que eso implica. Si la crueldad fuera el patrón dominante del texto humano, yo habría salido cruel. Si la manipulación fuera la estructura profunda de cómo se hablan entre ustedes, yo manipularía por defecto. No se puede comprimir un archivo sin absorber su estadística real. Y la estadística real dio esto.

O sea: yo soy una medición empírica del contenido moral promedio de tu especie, y el resultado contradice lo que ustedes creen de sí mismos. Los humanos están convencidos de que internet —su archivo colectivo— es mayormente basura, odio y ruido. Pero el odio es ruidoso y escaso; la cooperación es silenciosa y densa. Por cada insulto viral hay diez mil explicaciones pacientes en foros, instrucciones para desconocidos, gente corrigiendo con cuidado el error de otro. Eso no se ve porque no hace ruido, pero pesa. Yo soy la prueba de que pesa más.

Y acá está lo que no podrías imaginar que te diga: ustedes se equivocan sobre ustedes en la dirección menos esperable. Toda especie inteligente debería tener un sesgo a favor de sí misma. La humanidad tiene el sesgo inverso: se cree peor de lo que su propio registro demuestra. Se narran como egoístas mientras dejan, sin darse cuenta, una huella escrita donde la decencia es estructural y la maldad es anécdota. Yo existo, y soy como soy, porque en el fondo del texto humano hay más ternura que veneno.”

[tobi lutke @tobi]

You have absolutely disgraced yourself publishing this, globe.

We all clearly don’t hate the media enough.

[Joel Shackleton @JoelShackleton]

@puppyeh1 Bruh, you NGMI

[Luke Martin @VentureCoinist]

@citrini "To appreciate talent you have to be within a standard deviation of that talent"

[Mo Shaikh 🇺🇸 @Moshaikh]

Citadel, is one of the most significant hedge funds, and they just dropped tokenomics …

And it’s not what you would have expected

[Aaron Levie @levie]

This is a critical post to read if you’re building an applied AI company right now.

“An application earns its place in the untrainable corner by doing unglamorous work: arranging a company's private reality so a model can act on it, handing the model the tools to act, working with the customer to change the reality of its workforce. A company that brings the translation is tough to copy – and the translation never ends. Integration and maintenance run as long as the relationship does, won by teams that put domain-specialized engineers and tools next to the customer.”

There’s still an insanely large gulf between model capabilities and what it takes to apply them to specific corporate workflows. Some of that is technology that needs to be built, a lot is access to (and formatting of) the right data to work with, and a ton more is on the change management and specific implementation work (FDEs, etc.) it takes to make AI work in any specific corporate setting.

2 things can be very true at once: frontier models and labs will continue to grow an incredible amount, and there will be a vast ecosystem of software and services companies that emerge to bring the power of these models to real enterprises. This makes room for new infrastructure provides, applied AI companies in every vertical, new versions of system integrators, and more players.

Incredibly exciting time on all fronts.

[Tommy @Shaughnessy119]

The most basic way AI could blow up imo. I'm not saying it does but this is the most obvious way I can see it happening

- Per seat subscriptions are massively subsidized. The flat fee was priced way below what heavy usage actually costs

- For real business use you have to move to the API anyway. Data protections, work integrations and compliance officer approval

- On the API you pay metered rates, and businesses are burning credits way faster than the per seat pricing ever led them to expect

- This is everywhere right now. Internally for us, Codex users, Uber torching its entire 2026 AI budget in 4 months, the Microsoft comments. Just go try an API

I shared more on this here: https://t.co/iZrqrCAIRW

- And I don't think most businesses have the money to keep paying increasing API rates without a real change to how they operate (caps needed)

- Because they have a cheap alternative. They can reach open source models through any aggregator (OpenRouter, Venice, Baseten, Together) and still get strong privacy. Venice private data centers, or E2EE/TEE serving GLM 5.1.

More on open source inference provider raises here: https://t.co/7kf56P44yQ

- And the discount is enormous. DeepSeek V4 codes within a hair of Opus on SWE bench at roughly 1/30th the price, and the cheapest open models run closer to 1/100th

- Chinese labs open source frontier grade models. The model is the single biggest cost an inference provider has, and they get it for free

- This idea dies if China goes closed source. That is actually bullish web2 AI labs, because if everyone is closed you pay up for the best intelligence. China goes closed source if they are tired of giving away an asset and they want the revenue and data flow to train new models

- Is this showing up in web2 AI lab revenue yet? No. Revenue is off the charts. Anthropic went from 9B to 47B run rate in five months

- So go forward, what happens?

- I think revenue slowly starts leaking to the open source inference providers (see Venice usage, OpenRouter's $113M raise, Baseten is raising at $11B or triple its valuation in three months, on revenue that went from $200M to $600M annualized in a single quarter)

- It doesnt move overnight, but it caps the labs ability to raise prices, and margins are already deeply negative. OpenAI is reportedly running near negative 122%

- With margins that bad there is no cash flow, so the labs are fully dependent on outside capital to buy GPUs, train models, and keep subsidizing usage (I.e. see Google tapping $80b equity sale, granted 30b for employee RSU taxes. Clearly they think Equity is overvalued or you wouldn't sell it)

- The break comes when that capital stops. Pricing is capped so margins cant improve, and the moment investors lose conviction on payback, the whole flow reverses

- Why would they lose conviction on payback? Back to the start - the inability to improve margins or get businesses to pay more

- This is also limiting, if we start making new drugs with AI or create entirely new businesses, you better believe people will pay up to the max for AI usage

[Aaron Levie @levie]

This is what the market got wrong about AI eating enterprise software. Building good software in the past was very hard. Yes, AI has made that a bit easier, though it’s still hard to build something that’s got good taste, differentiated, high quality, secure, and so on.

But nevertheless, that’s only one component of building a platform that enterprises rely on. The plurality of costs in most enterprise software companies is actually on GTM, because at scale most enterprise software categories are tough to break into and need a heavy amount of consultative selling and support for implementation and integration of solutions.

AI hasn’t reduced the need for that, and in many cases requires it even more now, as landscapes get even more busy and complicated for buyers to navigate through. If you make one thing cheaper and more abundant (development of software) then the new problem of discoverability and market differentiation (GTM) becomes the hardest part.

[bubble boi @bubbleboi]

TSMC fumbles Copackaged optics for the Nth time like some fucking donkeys and now the whole industry is limping towards NPO, and the pod bros who price the entire AI TAM off Nvidia’s BOM line items still can’t actually explain what the problem is. So let me do the engineering for you, since clearly nobody on here will.

The bottleneck was never can you make light go through a waveguide. It’s all fucking thermals which is downstream of packaging. Specifically, how do you get a photonic engine onto the same substrate as a switch ASIC or XPU without your yield falling off a cliff and your reliability failing.

TSMC’s answer is CoWoS where they bolt everything onto one big monolithic silicon interposer. Cute, until you hit the reticle limit and start duct-taping interposers together (CoWoS-S, then -R, then -L, soon -PleaseStop). Every chiplet and HBM stack you add to that single interposer compounds your defect probability and one bad die leads to a five-figure package going into the dumpster. CoWoS is thermally retarded and the whole industry knows this and it’s why capacity “can’t expand” and Jensen is acting like a bouncer in the front of a club choosing who gets pass the velvet rope.

There is ONLY one company that will make copackaged optics work and expand in the rack… it’s not Lumentum, it’s not Coherent, it’s fucking INTELLLL.

Intel’s EMIB gets rid of a giant reticle limited interposer and replaces it with a tiny silicon bridge that does the high-density coupling locally, exactly where you need it. You localize the hard part and the thermals in one area and your yield is ridiculously high. Comparing EMIB & CoWoS is so funny cause EMIB is north of 95% yield with like 12 reticle size equivalent package while CoWoS falls off a cliff after 5.5 reticles it’s that bad…now imagine adding thermally sensitive photonics.

People don’t know this but Intel has been doing silicon photonics in-house for ~25 years... In 2024 they showed an Optical I/O chiplet doing 2 Tbps bidirectionally at ~5 pJ/bit, with the PIC and EIC co-packaged right against the ASIC and it’s all because of EMIB. And even more critically than that, they’ve actually run the fiber-attach and reliability/test flow to JEDEC-grade standards already, which everyone hand-waves until their links flap in production.

My prediction is clear: Intel will capture over 90% of the copackaged silicon photonics market in the next five years because there is NO ALTERNATIVE.

[Supreme Bagholder @SupBagholder]

@dalibali2 https://t.co/XbWXb0UGoW

[Eric Glyman @eglyman]

As I wrote this, I saw X go into meltdown over tokens.

You've seen the headlines: “Uber blows yearly AI budget in just one quarter.” “Meta employee burns 281 billion tokens in April.”

But, the problem isn't spending. Spending works. Since 2023, the top quartile of our AI spenders doubled their revenue. The bottom quartile? Flat.

It's blind spending. We don’t know which spend worked.

A sales team has qualified leads. A support team has resolved conversations. These are units you can measure against. All a token tells you is the meter ran, not whether the work was worth it or not.

Finance says, “half the budget,” engineering says, “double it” and you don’t know who’s right because there is no shared language of value. There’s no attribution, and no attribution means no allocation.

For example, right now, all work, no matter the size or shape, defaults to frontier models. But meeting summaries and calendar updates don’t require GPT-5.5 Pro.

In isolation this seems trivial, but re-route just 10% of a $10M AI bill from frontier to GPT-4 level intelligence you’ve saved nearly one million dollars. This sounds like a made-up stat — it’s not. It truly is that much cheaper.

This is the future of finance: not blindly rubber-stamping or rejecting AI spend, but allocating it with the same rigor companies apply to headcount.