Large companies can’t use those plans. The consumer or single dev plans appear highly subsidized based on the difference between rates for the same thing.
> If it looks like circular financing and smells like circular financing it’s circular financing.
Problem is many people don't know what circular financing is. For instance, pick one of Nvidia's investments and explain why it is a circular financing arrangement.
The real headline is that they couldn’t hit what they wanted in terms of valuation and funds raised. Just were not enough people willing to invest given concerns that it may be downhill from here for a while on AI.
This will also make it even harder to avoid any future IPO being a down round. They’re almost certainly worth much less than Anthropic and Anthropic is, per reports, struggling to keep its valuation much above 1T, and even that may fall through.
OpenAI is a bit more scattered brained and spread across multiple products.
Anthropic is way more focused. That helps in a way that builds upon another: their product tends to be better and the people's perception of it as well.
But "much less"? OpenAI needs a month or two of good choices, progress & announcements, and that flips. On the other hand, Deepseek could blow both out of the water unexpectedly, ending the argument about who has the superior tech.
There's also the Elon factor. Anthropic has a good relationship with Elon (to the point where he discounted the compute sold to them by quite a lot) while OpenAI/Sama is the devil to him.
> Anthropic is way more focused. That helps in a way that builds upon another: their product tends to be better and the people's perception of it as well.
But they are still not likely to be investment-grade at IPO.
mostly because they got all those 500B hardware commitments on balance sheet.
Without them they have best coding/other(e.g. most accountants prefer claude) model on the market, with solid increasing revenue channels and loyal customer base.
I disagree with this, most normies will never use Claude code... but they WILL use ChatGPTs various modes and apps that handle a lot of things for them.
Their recent "intelligent ui" (forget what they call it), which turns the chat almost into a magazine is amazing for people when they start doing measuring or responses comeback as little graphs or diagrams showing this or that.
Claude is still not able to generate pixel images.
I agree Claude is better for the likes of you and I, but I see the opposite in non-technical people which is most people
Who says selling to "normies" is a value proposition in the first place ? if we're heading towards a K shaped economy - being mass market is a bad thing, and serving professionals and top of the curve is where there's money to be made. The only money in this market so far is in selling to megacorps and governments.
Also Google will eat them eventually in mass market part as well.
Normie consumers will probably not ever spend more than $15/mo on LLMs as they exist currently if they would spend money at all so their LTV will probably just turn into race to the bottom performance marketing
Devs and the token-consuming services they create are probably a more valuable market than the entirety of the glorified search engine use cases that the average consumer is focused on
> Deepseek could blow both out of the water unexpectedly
This is tantamount to saying that the value proposition is unknown, if a supposed trillion dollar company could get upended overnight by a startup
Where's the moat, the unassailable first mover advantage, the enterprise lock intengrations that mean nobody could realistically move you out of the way even if they had slightly better tech ? If none of these exist, investors should be scared.
DeepSeek can't come out of nowhere to match them. They don't have anywhere near enough compute for that; Liang Wenfeng said as much in his leaked comments to investors. That's the moat.
What if I asserted that the MCP economy could be worth 5x more than LLM market since tools usually end up just being a fraction of the opportunity compared to market domination.
Maybe. The problem with the MCP economy is that it's not clear yet what shape it can take. If it takes the shape of API integration solutions, then it won't be 5x. If it takes the shape of an App Store, then yes.
I think arguments for either direction are valid. On one hand, MCPs are essentially APIs used by developers. Developers will demand some form of open reusable standard, "MCP gateways" or hosts will spring up to host them, hyperscaleres will offer them, and ultimately it will be another cloud commodity.
On the other hand, some of the target users of MCPs is the consumer market rather than the developer market. An App Store model makes sense there and the provider/platform can collect the lucrative 30% cut and end consumers’ numbers makes for massive revenue opportunity. This dictates a walled garden "Agent" like Muse or Instant.
If #1 is the direction the market goes in, then more batteries-included solutions like Muse or Hermes become the next obvious step up the chain. If #2 wins, then yes having your MCP available to on a Muse App Store that Meta takes a cut of some sort would be larger.
> How could anything else be bigger than Super Intelligence? Which is supposed to be the next step after AGI, which we presumably already have?
Meh. We both do and don't have AGI, because everyone before ChatGPT thought it was obvious what it meant and it turned out we all disagreed with each other about that obvious meaning. We can't even all agree about the "artificial" part, which is the most surprising part to me, let alone "general" or "intelligence".
If you applied some thinking for a moment and not spiraled out you probably would realize the the tools that control a market are worth less to sell themselves then to utilize them.
Not sure, but in the meantime they removed the option to right click "Open in new tab" on the "New chat" button (first one in the sidebar) in chatgpt.com
> There's also the Elon factor. Anthropic has a good relationship with Elon (to the point where he discounted the compute sold to them by quite a lot) while OpenAI/Sama is the devil to him.
The Elon association could be a long-term negative.
It certainly didn't help the Republicans in this last election even with Elon donating half a billion dollars to them (post 2024 Elon appears to be, like AIPAC, more of a toxic association than any amount of money gained can overcome), and there are reasons to believe that flip on the political side will eventually matter on the business side of things.
Elon's Texas "home base" just flipped blue in a big way and there are likely to be high profile investigations into whatever it was he was doing with DOGE.
And perhaps most directly important to Anthropic, unless the winds change significantly in terms of the politics surrounding data centers (and I suspect if anything they will get increasingly hostile, not better), I wouldn't be surprised to see the Memphis city council get purged of pro-Colossus members, replaced by anti-data-center candidates when the next elections take place in Oct 2027.
This would by my question. Why do they need money at all after just raising 9 months ago?
But none of these numbers are real. Softbank and MGX are re-arranging the deck chairs between OpenAI and Stargate so the actual new outside money here indicates very weak demand.
This is a press release to try to anchor the valuation but it doesn't seem like a lot of people are buying that.
I do expect them to IPO in ~6 months - they were planning to IPO in 2026Q4 but they torpedoed those plans, and Sam Altman said it's off the table for the rest of 2026. The implication is that it's on the table for 2027Q1.
Interest rates are the big wildcard. If this is the start of a significant rising cycle, akin to 2022/2023, then the AI bubble is toast and all these companies are dead. If the Fed pauses in December/January there may be a window of opportunity in early 2027 and we'll see both OpenAI and Anthropic IPO and possibly jump.
Rising interest rates are a triple whammy to AI companies: 1) risk capital always flees first when rates go up, so the available capital dries up 2) they and their suppliers have borrowed significantly to fund datacenter expansion, so rising rates will directly increase their expenses and 3) AI is considered an investment for their customers, and corporate finance always pulls back on more speculative investments when rates go up, and so their customers will likely pull back and directly shrink their revenue.
>> I do expect them to IPO in ~6 months - they were planning to IPO in 2026Q4 but they torpedoed those plans, and Sam Altman said it's off the table for the rest of 2026. The implication is that it's on the table for 2027Q1.
Whether they IPO depends on a lot of factors. For example, if we see a market meltdown triggered by data center moratoriums, then neither lab will IPO in 2027 at the very least. And if Anthropic achieves RSI first, there won't be much investor interest in a clearly inferior lab.
RSI has already been achieved, but it is not the infinite wealth, eternal life, ending all disease fantasies, and there is no monopoly, just more intense competition as everyone is capable of replicating it, so bad news for that investment thesis.
> I would think an RSI could count the number of R's in strawberry
Can you count the circles in that sentence?
Like, I think that RSI et al is way over hyped (where's the data gonna come from?) but the number of R's question is very silly given how tokenisation works.
No idea who's actually worth more than who here, but I will say that recently I've stopped using Opus at work for the lion's share of technical work. I used GPT-6.1 Sol for one big project I tackled last week, where the agents spent about 20 hours to produce ~73k LoC across 22 PRs. While the technical decisions and code weren't bad and design gaps were left clearly enumerated, the overall "human factor" was terrible, in the sense that the plan docs were overly-verbose and difficult to read and PR descriptions were abysmal. Numbers and words were run together all over the place where there should have been spaces. At that point I pointed Opus 5.5 at the whole thing and asked it to double-check design and code and rewrite all the "for human consumption" text in plan docs and PR description, and it did a phenomenal job of that part of it. Plan docs were made much more concise with emphasis on the strategic parts of the problem. Opus accepted the vast majority of the design and code that GPT-6.1 Sol had produced.
Of course I have no idea what the technical results would have been if I had just used Opus 5.5 end-to-end, but I'm fairly confident it would have been more expensive given the rates my company pays for each. For that matter I wonder how Kimi3.1 Pro or DeepSeek 4.1 Flash 1017 would have done with various parts of the job. In fact I may try rerunning the whole thing using open weight models next week just out of curiosity.
If Kimi+DeepSeek produce something roughly equivalent, then just from my own personal experience with a novel problem involving legacy in-house code, as opposed to public benchmarks for which I don't have a great handle on how well they correlate with value produced by the models, that will make me question the valuation of both OpenAI and Anthropic.
I use Opus 5.5 for planning, sprinkle in a Fable 5.1 review of the spec (they go back and fourth), then send the spec and plan to my local deepseek 4.1 Flash 1017 to implement. It crunches away for a good while (using ds harness)
Then check w/ Opus and Astra for good measure if it really matters. Works well. DSv4.1 is okay but does make mistakes. I run my 2x DGX sparks at 60-70% capacity this way, which nets about $400/mo worth of tokens on $30 of electricity.
I am hoping in the next six months to be able to in-house ALL of the above using a slightly more competent model, or two more sparks. It is slow running local, but it is really fascinating to have all this work done from my desk.
Developer sentiment seems to be awarding Anthropic on quality and efficiency with more usage (plus Claude Code CLI being earlier to market), although maybe OpenAI is in bed with enough non-coding enterprises that it has an edge there.
Is anyone actually using those features? I feel like this still very much just Codex vs Claude code, and if codex has the better model everyone will switch in a week.
All the other products feels like a (desperate?) attempt to create moat and friction for switching models.
I feel like all these versus arguments are absolutely opinion and preference, but really deep down do hint at a modification that will be hard to ignore as an investor.
If AMD and Nvidia could make the exact same thing the exact same rates, why would the stock price of one be higher than the other?
For me OpenAI doesn't have any stickiness/moat. I only use it because Sol 6.1 tokens are cheaper for similar quality for typical tasks. I also find it can be hit-or-miss more so than others when designing a system interactively.
Opus 5.5 came out more than a month and a half ago and is the clear favorite amongst developers, and OpenAI has yet to release something that can match or exceed it. That means they don't have their ducks in a row, and the internal models they do have take too long to prepare for general release.
"They're almost certainly worth much less than Anthropic" you type that with so much conviction. I have no dog in this fight, but I'm not so such. We have seen OpenAI provide models in Audio, Image, Video, etc. Perhaps it's for publicity, but their models have tackled difficult math problems and those that I know that use their top models are just as happy with it as they are with Opus 5.5. IMO, I think they are neck and neck.
Yes that is all interesting but the only thing that matters for company valuations is how much money they make, how quickly the amount of money they make is growing, and how much the assets they own are worth.
You can believe than anthropic is a better investment (“worth more”) than OpenAI while still thinking they’re both overvalued (or will underperform other investments).
Have both OpenAI and Anthropic made a fundamental miscalculation here (and a lot of misteps) by targeting the top end of the valuation? Surely can only go down right?
Weird, I've been told repeatedly that inference is wildly profitable for both of these companies and waves hands training costs are irrelevant for some reason.
It’s: we spent X billion to train our HUGE model and it’s so good we can make money off it. Please fund us for Y billion to build the HUGER model that will maybe destroy the planet, and if it doesn’t we can’t sell it back to users at profit because of legitimate security concerns. And then we’ll need Z billion to train...
Does anyone see the path to ROI here? There is clearly a profitable business model within these big AI labs, but it’s held captive by messianic 90-page IPO risk statements. I know they want to sell restricted access to the more capable models but the market for those kind of professional services doesn’t even exist yet.
Are there enough people using AI for coding and advanced math and physics who need even better models to justify these values? Because for "normie" non-coding tasks (searching, summarizing, writing) which it seems to me are what the vast majority of users would use, we have ChatGPT at work it defaults to the Luna 6 model and it seems fine as-is today.
I would be shocked if Anthropic IPOs below 1.25T. Prediction markets have it at 1.625T now. Even quite conservative Aswath Damodaran puts it at 1.45T.
I think once you go below that you can probably just sell on open market without any IPO dance like finding institutional investors.
Less sarcastically though the bet on how much AI company IPO at attracts a certain type of people. People who may have a certain believe about AI companies which will bias their assumptions quite a bit.
Prediction markets are sometimes wrong but they are very accurate on high volume markets like this one. Here we have hyperliquid perpetual futures among other things. Volume on those alone is above 10M USD per day.
>>Less sarcastically though the bet on how much AI company IPO at attracts a certain type of people. People who may have a certain believe about AI companies which will bias their assumptions quite a bit.
They're not very accurate. They are generally accurate with a margin of error big enough that they're far from a sure thing. If they were accurate then no one would take a contrarian position. I'd look at a prediction and say "well obviously the favored side is going to win" and put all my money there, over and over again, until I was the richest mortal in the universe.
Polymarket has it at ~50% that their IPO value is between 1.25T and 1.5T. Do you think that is representative of reality? It's not like we get to flip the IPO coin ten times.
>>If they were accurate then no one would take a contrarian position.
Sure, the price is the weighted average of expectations. People take either side for many reasons though. There would still be a lot of training in a perfectly efficient market because people and institutions have their own utility of money functions and other reasons to take bets (hedging their vesting stock for example).
>>. I'd look at a prediction and say "well obviously the favored side is going to win" and put all my money there, over and over again, until I was the richest mortal in the universe.
>>Polymarket has it at ~50% that their IPO value is between 1.25T and 1.5T. Do you think that is representative of reality? It's not like we get to flip the IPO coin ten times.
Yeah, it's the best guess we have.
>> It's not like we get to flip the IPO coin ten times.
That's very limited frequentist perspective. Just because you can't re-run the experiment doesn't mean you can't assign probabilities to events.
In theory though that’s the whole point of the prediction markets. If all analysts truly believe (with conviction) that the number should be <1.2T, then they can put their money where their mouth is in the prediction market that’s currently overshooting their predictions by 20-40%. If they don’t have much conviction, then maybe the stories in the media aren’t their true beliefs or they’re trying to push a narrative.
Why does HN have this "if they won't bet on it, they don't believe it" mindset?
In quite a lot of sectors, gambling on a prediction market for an outcome you can influence is frowned upon, unethical, even illegal.
To be clear, I am talking about the investment analysts who have a role in setting the IPO price, which is a (then-private) decision, not an outcome of a market. It would almost certainly be a crime for the analysts involved in pricing an IPO to make prediction market bets.
I mean unless you think the valuation multiple on AI companies have compressed by over 50% in the past week, the prediction markets seem pretty accurate.
OpenAI will be just fine, they are building superintelligence. I think these comments will be pretty funny in a few years. This is the best wealth building opportunity of my generation.
Even if it's restricted to a few companies there's still a fuckton of money to be made. 4 companies capturing ever-increasing slices of the world economy.
Calling superintelligence "newspeak" is proof you don't really understand what you're talking about. This is not a new concept and has been discussed extensively for about two decades.
This has nothing to to with the recent EO, it has been known for some time that the labs are racing towards ASI.
Because this is not a topic you're familiar with, I would recommend some light reading on it before returning to the topic and commenting on it with such confidence.
A good starting point would be reading some of the perspectives of some of the people that built the modern LLM. I promise you they understand the technology and its potential better than you, and were discussing these things well before it was even a concept in your mind.
Treating people like uninformed idiots for disagreeing with your choice of language. Cute. Executive order 14434 sure did a number on some of y’all.
Edit: sneaky edit bud. The term existing for a while doesn’t make the uptick in use of said term since the EO, right before trillion+ IPOs, to describe what the frontier labs are building, less of a “funny” coincidence. The people you tell me I should listen to standing to make big bucks on me believing them makes it, at the very least, ever so slightly suspicious.
The problem with your logic is that the history of tech is full of “good enough” eating “best” for lunch all day long. Anthropic’s plan to be the best is increasingly looking like a terrible business plan.
Most finance people I’m talking to think $200-400B is a fair price. That would be an amazing story in any normal situation but a total disaster here. However sane fundamental financials just don’t support a higher number.
Challenge is while you can play games with the float size to jack up the price as existing shareholders start selling you have to convince more and more people of a sky high price when all the fundamentals and the market pulling things in the opposite direction. Employees have been royally $&@ked in prior IPOs as that story plays out.
1) SpaceX is trading below its IPO price. If you bought shares at the IPO you’d have lost money, unless you sold on the pop.
2) Valuation aside, SpaceX has a massive moat. It’s crazy hard to do what they’re doing. Anthropic increasingly has zero moat, with the market rapidly coalescing around commodity open models.
It remains to be seen whether SpaceX just drained their own moat when they canceled Falcon 9.
They’ve now got all their eggs in a new basket. A basket that isn’t entirely in working order yet, and whose market viability is still uncertain because it remains to be seen whether a market that’s used to panniers really wants a laundry hamper.
um, they've got 2 years before the basket is retired during which time they can always extend if they need to. why would they want to keep a less capable, more $/lb into orbit system going after Starship becomes a viable, reliable upgrade???
But they have already stopped taking orders, which means they’re already clearing their pipeline and it will take some time to restore. Launch contracts don’t happen overnight.
$/kg to orbit is not as important a deciding factor as many people assume it is. It’s typically a small portion of overall costs, and there are often cases where a launch provider that’s less expensive in terms of $/kg to orbit is actually more expensive in terms of total cost.
Starship is going to be a particularly weird one to adapt to. The “deploy out the side” design may make it straight up incompatible with a large subset of spacecraft. For those where it is workable, migrating commercial payloads to it may still require the development of new satellite buses, which is something SpaceX doesn’t seem to be working on for the benefit of anyone other than Starlink. And such a large rocket means most potential customers will have to plan on ridesharing with even more co-passengers, which means even more room for scheduling conflicts, compromises on initial orbit (and therefore cost to reach destination orbit), etc.
That’s just assuming Starship development goes smoothly from here on out. Which seems optimistic considering that, even by the standards of spaceflight, its development thus far arguably qualifies as cursed. Considering the gap between original design goals and reality is already historically large, I certainly wouldn’t be taking any cost estimates at face value right now. Like for any launch vehicle program, we won’t know its true capabilities and costs until it’s operational.
You haven't spent much time with the latest self hosted models then. Give it a good harness and instructions, access to a web search engine and ability to iterate on problems and they do a good enough job that I'm happy with the results.
Why is it unbelievable? I still remember how to program and arch new features and don't need claude to tell me how to do it. It is much more enjoyable to do a little work on your project and offload the grunt work to a weaker model then just being a highly paid merge pr button pusher for whatever opus decides.
This is what I've been doing with qwen3.8-flash-next. I haven't fully let go of the reins yet but I do like having a junior who can implement my new features as I have designed them
>I forgot Perplexity even still existed. They went from all the rage to nobody talks about them anymore.
A lot of the early hype was driven by how liberally they were handing out free Pro memberships. For a while, every telco, bank, etc. was handing it out as a free promotional offer. I don't think anyone I know that raved about it ever gave them a single dime.
Their product was definitely cool for a few months, but they had zero moat to begin with (considering how quickly the frontier labs caught up), and the conversion rate on those free sign-ups must have been abysmal, especially after they nerfed the free Pro subscriptions on both quality and quantity dimensions, and their own "politically neutral" DeepSeek R1 distillation didn't pan out.
Name ID. They were around early and got their name out there. If you don't keep up with the blow-by-blow of the tech and the surrounding market, you may not know that there are better alternatives available.
If there's no moat then there's no need to be skeptical about a company with hundreds of millions in revenue. Their brand resonates well enough for that.
I wouldn’t be surprised if they pull the plug on the IPO and go hide under a privately funded rock.
The second one of these AI companies gets a fair valuation and folks start booking losses the whole AI house of cards will come
crumbling down. The crazy thing is if they drop below around 1T some existing investors will be booking losses.
A realistic valuation is likely in the hundreds of billions, which would be a total disaster and thus they’re going to do everything possible to avoid that.
reply