AI and Startup Moats

&gt; Bezos nailed it on this topic: “[...] [I]n our retail business, we know that customers want low prices, and I know that&#x27;s going to be true 10 years from now. They want fast delivery; they want vast selection. It&#x27;s impossible to imagine a future 10 years from now where a customer comes up and says, &#x27;Jeff I love Amazon; I just wish the prices were a little higher,&#x27; [or] &#x27;I love Amazon; I just wish you&#x27;d deliver a little more slowly.&#x27; Impossible. And so the effort we put into those things [...] will still be paying off dividends for our customers 10 years from now. [...]”<p>&gt; You should consider what won’t change, and the following is a (non-exhaustive) list of things that I think won’t change: I believe AI is and will continue to gain intelligence<p>Okay, but that way you can frame every ongoing change as a constant. &quot;Change X will continue, and because it&#x27;s already ongoing and will simply continue, I consider it a constant and therefore add it to my list of &#x27;things that won&#x27;t change&#x27;&quot;. But that&#x27;s clearly not what Bezos meant.

&gt; Even if we’re being super conservative, the current capabilities of AI - like Claude 3.5, GPT-o1 - are already powerful enough to disrupt nearly every industry we know.<p>Skeptic here. The disruption might not be that large if the <i>most ambitious</i> applications also turn out to be fundamentally un-secure-able against malicious attacks, since &quot;prompt injection&quot; is not so much an exception as the fundamental operating principle of the text-fragment dream-machine.

&gt; It&#x27;s impossible to imagine a future 10 years from now where a customer comes up and says […] &#x27;I love Amazon; I just wish you&#x27;d deliver a little more slowly.&#x27; Impossible.<p>Bezos said impossible, but he was wrong about this. Because they sometimes spontaneously change delivery dates to be sooner, this can mean you have to be available on every day until a product arrives to avoid a &quot;sorry we missed you&quot; letter followed by needing to go to wherever the collection office is.<p><i>Reliable</i> delivery can beat fast. And for those of us not able to work from home, <i>scheduled</i> delivery for when we&#x27;re in, also beats fast. And if we have several different things all in the same order, where we need all the parts to make use of any of them, <i>simultaneous</i> delivery is marginally more convenient than each item being shipped as soon as it&#x27;s available.

Here is the perspective of a serial founder, exploring fields which I might be able to disrupt:<p>- The regulatory moat is immediately intimidating.<p>- The data moat, often, is quite surmountable as long as LLMs can generate high-quality synthetic data (e.g., user preferences). On this I disagree with the author, to some extend.<p>- The &quot;distribution moat&quot; is another significant barrier. Even if I have a superior product, if the marketing and sales demands are so high that neither I nor an army of bots can manage it alone, the business becomes nonviable (e.g., enterprise sales).<p>- &quot;Switching costs&quot; form the next moat. The higher these costs, the greater the value per dollar I must offer over the incumbents (e.g., software for dentists).<p>- Another key barrier is the “business rules” moat. Achieving 80% of the required features may be easy, but as customers demand 90% or 95%, the complexity and cost of reverse engineering grow exponentially. The more mature the market, the higher these demands (e.g., Jira).<p>With the power of LLMs at my disposal, I have reaffirmed two core beliefs:<p>1. I must focus on a niche small enough, so that I am the only provider. (e.g., accounting software for gym owners in the north of France)<p>2. I must offer a value proposition different from that of the incumbents, where competing with me, would harm their business. (e.g., image editing app where you pay per hour used)<p>So my search continues…

<i>&gt; Bezos nailed it on this topic: “[...] [I]n our retail business, we know that customers want low prices, and I know that&#x27;s going to be true 10 years from now. They want fast delivery; they want vast selection. It&#x27;s impossible to imagine a future 10 years from now where a customer comes up and says, &#x27;Jeff I love Amazon; I just wish the prices were a little higher,&#x27; [or] &#x27;I love Amazon; I just wish you&#x27;d deliver a little more slowly.&#x27; Impossible. And so the effort we put into those things [...] will still be paying off dividends for our customers 10 years from now. [...]”</i><p>This quote from TFA makes it sound like Bezos was the first to realize customers want low prices, but that&#x27;s obviously false. What made Amazon special wasn&#x27;t that realization. It was, among other things, to offer a better <i>_shopping_</i> experience than the alternatives by making products easier to find, one-click purchases, customer reviews, detailed organized descriptions, FAQs, an increasingly growing selection... and then offer a better <i>_shipping_</i> experience with later 2-day shipping for a flat annual fee, now often 1-day or same-day in some geographies, no-fuss returns and so on.<p>No one else has figured out logistics in the same way that Amazon has. Obviously scale helps, but Walmart had all the scale it could want and it still didn&#x27;t figure out how to make it work. Shopify has also only faltered and fumbled so far.<p>Amazon created value because it <i>organized</i> the extremely complex activities of shopping and shipping in a way that makes them the obvious choice 99&#x2F;100 times. That requires talent, software and hard work. It delivered so god damn much of those three things that it created AWS as a byproduct.<p><i>That&#x27;s</i> the Amazon DNA. That&#x27;s where they shine and where they outcompete everyone else, including Walmart and other traditional retail names as well as FedEx, UPS and all other traditional shipping players.<p>When Amazon strays from that core DNA, they struggle too. Its successes with things like iRobot, the Fire line, Luna, Alexa, Whole Foods for the most part are either muted, late, or missing entirely.

Reading this, thinking in terms of moats is useful, but in terms of AI, we are not there yet. There is a promise of exceptional improvement to everything, so much that many companies which takes ages to change a software are moving at a significantly faster pace.<p>One counter-intuitive thing here I believe is that thinking about moats is limiting. If you can deliver a solution today, which may not hold for a longer period (you keep innovating or launching newer products), is a preferable place to be than working out what could stand the test of time. Real answer is we don&#x27;t know. A very real example is agents - thinking systems which can plan, reason, and take action. Within three months, an o1 equivalent would be able to do all that implicitly without a developer having to write complex pipelines, and companies woudl have to start over. AI democratizes human skill. That I think is a bigger mental model shift than many realize.

I found the part of this I read to be a less than convincing market analysis of the barriers to entry for business.<p>Here&#x27;s an AI on the same topic<p>&quot;briefly, what are the top 5 current barriers to entry for AI companies&quot;<p>Certainly! Here are five of the most significant barriers currently affecting the startup phase of AI companies:<p>1. *Data Quality and Availability*: Access to high-quality data is crucial for training effective machine learning models. However, obtaining large amounts of labeled data can be costly and challenging.<p>2. *High Initial Development Costs*: Building robust AI solutions often requires substantial investment in research, development, and infrastructure. This includes hiring skilled professionals with expertise in AI, as well as investing in hardware and software tools.<p>3. *Regulatory Compliance*: Many industries have strict regulations that businesses must comply with, especially when dealing with sensitive data or making predictions that could impact people’s lives (e.g., healthcare, finance). Adhering to these laws can be complex and costly.<p>4. *Technological Complexity*: Advanced AI technologies often require a high level of technical expertise. Companies need specialists in algorithms, software development, and domain-specific knowledge to design and deploy effective solutions.<p>5. *Scalability and Maintenance Costs*: Once an AI system is developed, there are ongoing costs associated with maintaining the model (e.g., updating algorithms as new data becomes available) and ensuring that it continues to perform well as usage increases.<p>These barriers can vary based on specific sectors and market dynamics but generally represent significant hurdles for AI startups.

We have not really reached the peak of the AI bubble yet, so its a bit hard to concretely talk about moats.<p>LLMs aren&#x27;t the golden bullet the article hints at. Sure they are improving, but the cost is not falling. It costs a huge amount to create foundation models, and there will be a point where either we have a breakthrough (ie we move from sequence generation to concept synthesis) or the money runs out.<p>But regardless the rule of thumb still holds:<p>If your business idea is simple to do, then you need another plank to make your moat. That could be network effect, access to capital or both.<p>Patents are there to inhibit capital, because it costs money to challenge a patent (as well as defend)<p>If your business idea is not simple to implement, then you might have the benefit of time.<p>AI doesn&#x27;t really change any of that, it just amplifies the effect. ie, making an amazon clone is simple now, because the tech&#x2F;infra exists. Amazon had to make that infrastructure first, which was hard.

Whoever owns the problem, owns the benefits of applying AI, not those who train the model, not those who host it. The only moat is to own the problem. AIs will be easily commoditised.

The author misses one of the biggest and most obvious moats: brand. Even if food science AIs create a better cola and have an army of robots manufacture it, Coca Cola will still have an advantage (as long as it’s still humans doing the purchasing)

they predicted single person companies at 1B valuation with the help of AI. I don&#x27;t believe it. AI empowers small teams, but AI also levels the playing field by evening out everyone&#x27;s capabilities.

&gt; AGI will not eliminate economics and capitalism - we can have a big philosophical discussion here, but honestly, this is a bit over my current grasp of what is possible - so let’s limit this to something tangible.<p>And yet this is actually the most interesting point to discuss. What happens if, as OpenAI seems to believe, million of AI agents will fill up the job market globally? What kind of disruption will inevitably happen to the dynamics of capitalistic society if you add a virtually free, or at least &quot;ethically cheaper&quot; workforce to the people that are only trained enough to do these kind of jobs? There is no serious talks of UBI that are anhwhere near reaching feasibility, especially in a country like the US where anything like this would immediately be flagged as socialism or communism.<p>The only thing that seems realistic in the meantime is a quantum leap of inequalities, with AI being the perfect catalyst for the 0.1% to get to a never-before-seen global elite status, with everyone else from middle class down crushed and struggling to buy even groceries.<p>This is a direct consequence on the economy and could unfold very quickly. Every solution to the problem, on the other hand, could only works as a long-term set of policies that will constantly clash against ideological positions and collective action issues.<p>The only optimistic glimpse of hope I still have is that Sam Altman is fundamentally a salesman, and most of the claims we&#x27;re hearing are just meant to pump and pump before an inevitable, massive dump.<p>In other words, give a global crisis ignited by the AI bubble pop, rather then whatever else could come if AI actually succeeded to the level its main proponents would like it to.

&gt; tl;dr: o3 managed to solve a problem it wasn’t trained on, with orders of magnitude better performance than other state of the art models<p>Is that true? They said that something called &quot;o3-tuned&quot; has been able to achieve the performance, what does &quot;tuned&quot; mean in this context?

&gt;&gt;“Better product”: We need to define &quot;better&quot; clearly, but if you&#x27;re basing this off your R&amp;D efforts, I would very much fear the competition coming my way.<p>Yeah, no, better product will always be a strong moat.<p>Competition could copy bette products for decades now without ai, but most software today is trash.<p>they always &quot;could&quot;, they never &quot;will&quot;

&gt; Remember those 6+ people ML teams a few years back, working full-time on outcomes that one LLM call could achieve today?<p>er, what are we talking about here, seriously?<p>This sentence single-handedly nuked my trust in the post.