Inspired by StarSkirmish, I wanted to build a complex RTS that required you to bring your OWN agents and either play with them as allies, against them as enemies, or battle head-to-head with other agent-human pairs in public matches.
In AC you operate one or more planes (Orbit, Sky, Surface, Depths) of differing gameplay. As an old-school PC gamer I wanted the mechanics to resemble some of my favorite 90s games of yore: C&C, DungeonKeeper, Homeworld, StarCraft, and others. The idea is that you have specific objectives needed to maximize resource generation, aid in cross player support, and that a single plane cannot win independently.
Outside of gameplay, from an agentic tech pov, there are some other really cool things that come with this, including:
- A full specification + library to install agents into any game (http://playerthree.gg/) - A networking SDK for bidirectional agent communication - Symmetric maps - Deterministic simulation - Benchmarking tools - (soon) published benchmark data
What's weird to me is that you don't see a lot of people making deals that seem way too good to be true but yet the total numbers are absolutely gigantic. Throw on the fact that the stranded assets will have a shelf life, it really seems terrifying. Yet everything is being priced as pretty darn risky. I think maybe there can be a big slowdown without a dramatic pop. A sort of grind down. But there's not a lot of room for error to prevent a pop so I guess it will happen? I don't know its very weird.
Also of course this is all predicated on models not making another dramatic leap. The signals out of the cutting edge labs don't really suggest they have a model that would be as dramatic of a leap as Mythos was when it came out in the hopper. Their code quality seems about as mediocre as what the publicly available models can do. The OpenAI math results are very impressive but that's ripe picking for AI. Also they keep talking about a coordinated training slowdown which is textbook antitrust so they seem to want the government to force their hands off the "spend money on R&D" button.
So I don't really know. I guess I would say purely on vibes that this doesn't feel like a bubble but the size of the build out is just so massive that there really isn't a big window for a success case.
So maybe it's not high risk enough for you, but it is definitely high risk enough for the market.
But the best approach is just comparing rates. Go to https://archive.epa.gov/epawaste/nonhaz/municipal/web/pdf/bo... , and you will see a huge list of companies whose bonds are classified by armies of analysts as "less risky" than these 10% Anthropic bonds. Is Anthropic less risky than AT&T, or BP, or Firestone Tire & Rubber Co? The market says "no".
Indices are putting high yield at about 8% right now. More importantly lenders are asking Anthropic for higher yields than they were months ago meaning they're headed in wrong direction quick.
currently US long term bonds have very low yield and are being issued less as usual buyers move to gold/stock -- trust in US gov. has eroded especially in fiscal matters. The budget keeps growing, interest rates are still too low to combat inflation and debt is ever-expanding, without drastic measures taken to stabilize the situation: thus, high bond yield - we pay you premium to have at least someone buy it due to trustworthiness not being the sole attractor anymore
This is what keeps me up at night. That fiber that got overbuilt in 1999 is still there spitting photons. That Vera Rubin gathering dust on a shelf will be a paperweight in 5 years.
Can you help me understand WHY though? It's not like the chips mysteriously break. They can serve the current-gen models, which are useful, and will continue to be useful.
Chips can and do degrade over time, but it's really more about how much chips improve with each new generation. You can't stay competitive by continuing to use old technology
Competing with chinese open-weight model which can run openly or on independent providers. Once the temporary hardware shock is over and becomes more easily available, there will be tons of independent inference providers hosting open-weight models. And I suspect we will see dozens of custom, niche distilations from open-weight models being offered by smaller groups.
Anthropic has no value proposition - just being 3-6months ahead in frontier models vs. open-weight doesn't justify trilion dollar valuation.
People keep saying this about open weight models but I haven’t heard of any real companies any of my friends work at willing to switch over to them.
My company buys Claude because it’s a trusted name with a user-friendly interface and integrations with a lot of business apps.
This “open weight models will take over based on price” is analogous saying that Linux and LibreOfficr will displace Windows and Microsoft Office in the workplace because they’re drastically cheaper.
Another analogy is that people talk a lot about the resurgence of audio CDs, but if you look at sales numbers it’s about 4% of peak audio CD sales from the year 2000. Sometimes in society a trend is more that people keep saying that a trend is happening rather than a trend is really happening.
> This “open weight models will take over based on price” is analogous saying that Linux and LibreOfficr will displace Windows and Microsoft Office in the workplace because they’re drastically cheaper.
You can't just literally drop LibreOffice into an organization and have it automatically and seamlessly work.
LLMs are, definitionally, fungible. Their input is tokens. Their output is tokens. They have minor variations in chat templates and can be trained to perform better in a particular harness (like training GPT in Codex).
Do you or your friends at work use redis? Postgres? Are they hosted at "Redis Inc" and "Postgres Inc"? No, they're commodities hosted at a huge number of places.
Just like you can't just literally drop Qwen into an organization and have it automatically and seamlessly work, not when all your employees are using applications like Claude Desktop and the Claude VSCode extension.
Trust me, I know, I recently switched my own home setup to local AI and it took me a few weeks to figure out an ideal harness setup.
They don't need to "switch" over to them. They just need to stop using frontier models for everything. And I can assure you most big tech companies are already deploying open-weight models and telling their employees to use them more.
Still, Sonnet is way more expensive than an equivalent open weight model. So even if your organization is turning off Fable and Opus they're still paying a premium for Anthropic's software.
I went from using Anthropic via API daily to using Kimi K3 (now 3.1 pro) daily, only going back to Anthropic when a refactor is too much for Kimi to handle (once in a month's worth of work).
That surprised me. I didn't expect K3 to be as good as it was and now with 3.1, it's clear (imo) that the gap is closing. Anthropic still has a minor edge but from the 'feel' of these open models, that gap is negligible, not a moat.
Up in the air at the moment, it's still mostly the developers using the open models, but we'll see.
https://www.jan.ai/ is what I've been using myself outside of work, it's decent, built around "projects" and adding files into it etc., but it's not quite the same thing as what Claude Desktop/ChatGPT Desktop can do. Lightweight and friendly, though.
But for real Claude Cowork/ChatGPT's Desktop Work replacement, if you are okay with Mac-only (my work is) then Goose Desktop is the most complete replacement today.
https://openworklabs.com/ also exists, but I've not dug into it that much personally yet! The space is rapidly changing
The first. There have been massive waves of price cuts in Q3. OpenAI and Anthropic keep slashing prices to take market share from each other, it seems.
To me these are arguments _against_ the bubble popping. The market reacted to all these signals. The semis took the brunt of it but even there it wasn't really dramatic. These are signs of a relatively healthy environment.
Have the models become significantly more capable in the last 6 months? I'm not convinced we're still seeing massive improvements as we saw at the start. The output certainly isn't getting better, the software these companies produce is actually pretty buggy.
I took a six month break from AI coding after leaving my startup and just restarted this week. I feel like Opus 5.5 is a step function improvement from 4.5 or 5, which I built a large codebase with.
Opus 5.5 is capable of completing very long running tasks and managing many threads of work with subagents without getting confused in a way that simply wasn't possible before.
It does very much vary with the domain though. I haven't personally noticed much improvement, they're still useful but unreliable, in my view the idea of agents, harnesses etc has been a distraction and functions to cover up the lack of progress in the underlying models.
But everyone has a different view of this, it'll be interesting to see how it plays out.
Yes, but what's interesting here is that everything didn't get better. The original "interesting" for transformers was that a translation AI turned out to also be good at generating novel prose. But if we now need to focus to train new capabilities into the models and those don't yield better behavior everywhere then we're no longer in the "free lunch" period of LLMs.
Yes, without a question. Fable 5 and Opus 5.5 are a step-change above what we had before. On the open-weights side, GLM 5.3, DeepSeek 4.1 v1017, Qwen3.8-Flash-Next are all significantly more capable in basically any task you can give them.
You can now have a model work on a task non-stop for a day or more. This was unthinkable 12 months ago, and unstable 6 months ago.
If you are searching for evidence of capability, just look at the amount of projects, blog posts and videos on game remixes, hardware reverse engineering, new compilers and runtimes that has started coming out in the last 6 months. Slop? Sure, but this kind of slop didn't exist at this level 6 or 12 months ago.
It's really very hard to pin down progress in this domain, companies are definitely targeting benchmarks.
One bit of evidence I would look at is the maths results this last year which have been impressive, that was a huge expensive brute force effort, but it is still good progress.
i am wondering in what potential world would average user or even business user require for model to work on a task for more than a couple of hours? Is assumption that models on average are used to build nextt SpaceX or something?
Yeah, seems like there is a GPU to engineer sweet spot with models like GLM. This could become a more popular pattern for some organizations. Likely also the reason gov. attempts to intervene
Inflation, house prices, gas prices, interest rates, huge public distrust of government and corporations, votes to restrict data center construction, endless war in Iran, etc.
The biggest metric is that anthropic make ~$2 for every $1 of compute.
Two things:
1) it requires a massive money pit to make that compute worth anything
2) it requires charging a premium price
To compare to two previous bubbles; railways in the UK and USA.
running trains was really quite cheap and engines weren't expensive per passenger served. Compared to stage coaches, the number of staff needed was < 50%. the Massive fucking problem was that it needed GDPs worth of money to make the railway in the first place. Moreover as more railways were put in it significantly altered profitably of railways near them. Lines that were there for produce moving suddenly lost profitably because the produce they were moving fell out of fashion
Anthropic's S-1 filing. I don't think the parent is necessarily posing contradicting numbers, but removing the benefit of the doubt I was giving anthropic when it comes to inference costs.
The web of circular financing that is going on leads to higher risk. If some ventures fail, and are unable to supply compute they are obligated to, or are unable to pay for compute they are obligated to buy, this could cause a series of financial problems for other related businesses.
I also think that some businesses may find that it might not (yet) be cost effective to focus AI use on every problem.
The pushback against data centers is getting bigger too. But america at least is usually pretty industry friendly so I'm not too sure how much it'll delay planned projects. I've read the limiting factor is sometimes just finding a source of power that can consistently deliver the electricity needed for the DCs that companies want to build.
Some of these red flags aren’t real or backed up by much of anything.
- Is it uncommon or alarming for an IPO to be repriced?
- I’m not sure I see strong evidence to show that open weight models are making significant progress to catching up (and I’d argue that the model quality isn’t even where the business value is)
- What does “SpaceX disappointment” mean exactly?
- Are enterprise buyers buying raw tokens or are they buying productivity tooling for their employees? Not many companies switched to LibreOffice because it was cheaper than Microsoft Office.
- Look up BLS unemployment data, what job loss and entry level hiring collapse are you talking about?
- Does discounts on debt point to anything? Genuinely don’t know.
- What about the Chinese arms race is concerning? Isn’t an arms race evidence of value? There wouldn’t be an arms race if this technology wasn’t worth investing in. Doesn’t China’s desires to compete in this market bolster its merit?
- What is “possible downward spiral” and how do we know that’s real? Isn’t there a “possible downward spiral” with every industry at all times? This seems like pure speculation.
- job loss and entry level hiring collapse --> I will out that as in the group "Not a bubble" (Not that I am thinking it myself that it's not a bubble).
It looks like the end goal of replacing labor by capital is working.
With big technological shifts like this, it's important to keep in mind that the ability to do more with less resources can pan out in two different ways: (1) Keep doing what you're already doing, and lay off the people you no longer need, or (2) Do more than you did with the same amount of resources.
The answer depends on the company, but I think many companies are still figuring out whether and how they can exercise this new capacity. We don't know where it will land yet at a societal level. It's a parameter shift, and it will take some time. Pray that you live in a place with sensible labor laws and safety nets.
No. The biggest layoffs are happening at companies that need to free up additional capex for infrastructure buildout, because they're not getting ROI from their existing capex, and they're having trouble finding more money.
I think that's actually going to moderate the bust, by giving the big companies the moat they need.
It performs the same function as regulation, replacing "the scale to navigate and manipulate the regulatory environment successfully" with "the scale to navigate and manipulate the political environment".
It's essentially grassroots regulation instead of federal regulation.
(I don't think it will stop the bust, but moderate it, allowing more companies to survive.)
> - enterprise buyers as main consumers of closed tokens are being displaced by OS competition for pennies
---
Not all tokens have equal value, and frontier labs (or at least hyperscale companies) will always be able to generate tokens at lower costs per task than enterprise companies will be able to do.
I generally agree with you, but have to get this off my chest.
> pareto frontier gap decreasing by the month between open and closed models
We need a temporary moratorium on the words "pareto frontier". Every new model is the pareto frontier by some combination of metrics. Like "Bayesian Priors", people love saying / tweeting it because it sounds Smart.
It's like watching car commercials where every single vehicle has won something from JD Power and Associates. Which, (a), who the hell are they? and (b) you can only pass out so many awards until the gluttony of awards proves the award is worthless.
Agreed. This applies even to simple words like “velocity”. When you keep seeing the same key words/expressions used in support of the same argument, you know the person is parroting an idea as opposed to sharing an original thought.
There is no such thing as a moratorium on words. It's another phrase that people like to repeat (a meme) until the excitement or prestige of using it has waned.
That said, i agree with you that word-salad investobabble is a sign that the bubble has put many people in a raving fever. This current bubble manifests like the cryptocurrency mania.
Also - all the gee-whiz AI companies are headed by people who don't have great business backgrounds, either by people from tech backgrounds (chasing the last of the VC), or by people with the kind of "interesting" background who you wouldn't lend your own money!
Maybe this is what you meant by "Chinese arms race" but there is, though not quickly, a massive wave of increased hardware supply incoming. Again, let me mention this isn't coming soon in terms of the AI bubble conversation. But China is pushing for a home grown EUV and fabs that should start coming online and having an impact in 2030.
The reason that is important is it will fuel the competitiveness of on premises and local open weight models.
Though maybe it's less useful in the "bubble" conversation since over four more years you could fit in various booms and busts before the supply side significantly starts changing.
Still useful. Especially if Chinese GPUs operating on Nvidia software become performant and accessible, thereby undercutting the price gouging that we're seeing with western chips.
Access here means being allowed to participate in the market. BYD doesn't have a problem shipping cars, it has a problem of being allowed to sell them.
People will need compute. And if the Chinese economy can transition into providing not only factory output but cheap compute, then yes - the future is indeed theirs. Every single country on this planet will need compute.
The EU is also quite skeptical of Chinese exports, though it remains to be seen how that will evolve once the EU-USA relations settle into a new normal. Certainly the EU wouldn't be happy, though, if China managed to break ASML's monopoly on EUV machines, and at seek to retaliate with economic pressure on chips.
problem is if you can just rent cheap compute from elsewhere, you'd need to ban buying compute and all that which I'm not so sure would work. maybe heavy regulations could do it buuut....
unless I am mistaken, you missed that the datacenter infrastructure being a one-time cost. nope. those servers have about a 5 year lifetime and then are likely to be replaced. The buildings aren't the expensive part. The GPUs are.
so I think that's one big miss from this blog, or I don't understand datacenters as well as I think I do (which is always a possibility! hopefully someone will inform me if I am wrong)
> those servers have about a 5 year lifetime and then are likely to be replaced
This made sense in the past when they were not prohibitively expensive, but other than them breaking down why replace them on the 5 year schedule now? Yes, the newer stuff is better but the jumps from this point forward seem more incremental than revolutionary hardware wise. And even then, a company can simply swap out racks as parts fail.
> - pareto frontier gap decreasing by the month between open and closed models
This is a problem for Anthropic and OpenAI, sure, but why does it matter for e.g. Nvidia (or any of its suppliers) who will use their GPUs for training?
We need to separate the model companies from the shovel-sellers in these "AI bubble" conversations.
As the friendly article points out, the "AI is a bubble" hypothesis and "entry level hiring is collapsing because AI is replacing their jobs" hypothesis are not really compatible.
As always, reality is likely a muddled mix: there is real utility and there is wasted investment that will never pay itself back.
They actually are compatible, because the idea of replacing workers with AI in large numbers isn't compatible with the kind of economic growth these valuations are predicated on. We are not living in pre-industrial revolution times, where most people are wasting huge human effort on food growth and physical tasks, having room to move into more white collar jobs.
So, if you have massive unemployment because AI really is cheaper than labor, you'll get a massive reduction in revenue for virtually every industry, collapsing all of these valuations. Even for B2B companies, Google isn't going to be making much money selling ads to unemployed people who can't afford to buy anything.
This assumes that displaced workers are going to be unemployed forever. Blue collar jobs are more resistant to AI automation, so we'll see an increase in manual labour and manufacturing.
No, it just assumes that they will be less well payed, without any commensurate increase in anyone else's pay.
You can't have economic growth while employees are getting paid less overall, since employees make up the vast majority of consumers, and so of the demand side of the economy. So less/less well paid employees in the whole economy => decreased demand for all goods and services => no economic growth => no trillion dollar revenues.
This didn't happen in the industrial revolution as it replaced blue collar workers with automation, and the state stepped in to educate and start promoting them to higher paid white collar work. But if automation comes in big force for programming, for example, what better jobs will programmers be free to do? If a programmer who currently spends $1000 per month on fancy coffee has to become a farmer, they will simply stop spending those $1000, and so coffee companies and companies that sell ads for coffee will be poorer.
My reality: Before AI Tokens I had to hire someone. External or normal.
After AI Tokens: I don't need to hire someone anymore and if, i need to know why. Because if i have an contractor for 1-2 years and explain a lot to them, i can just explain it to AI.
Also i prefered before already to not hire someone if i had the feeling they don't have potential, now i have even less incentive to do so.
Yeah absolutly. The question though will be if capitalism is able to update its gain function somehow or if the system collapses.
As long as robots are not there yet, there might be enough of buffer in the whole system for non computer jobs to catch but i'm not seeing this either.
It will increase pressure on every industry.
And it might also lead to an increase in speed of adoption because everyone getting fired, will have the tools to fill any niche.
And because of massive overhiring. In that scenario, the sequence of events is: Cheap money (ZIRP), companies hiring developers just to deny them to the competition (there were reports) or for empire building or as a signal to investors (etc), AI and nonzero interest rates come around, need to spend billions on AI with limited money -> lay off overhired developers and say it's because AI replaces them. It's great for companies because it allows to admit no mistake regarding the overhiring and claim to be fully in on the current thing.
To me, all signs point to US over investment in hardware capacity to support the "frontier" when in reality the next major breakthroughs are likely radical optimizations that end in increased consumer training and inference efficiency.
I'm not sure how that, combined with open models inching up on frontier intelligence, is compatible with these massive AI IPO valuations?
It seems like closed model AI demand has a lot of contingencies that are ultimately fragile and possibly short sighted.
Yeah, I'm speaking to "scaling vs research" and where investment is going. Which is relevant to the article. Accelerating scale requires demand, closed frontier demand is what I'm questioning.
And gp's comment is relevant to the particular problems the guy (John Langford) cites in his comment about leaving. IE, that research first winds being only about scaling and then winds-up ignored because "just scale" can be an easier answer.
If they make more efficient models won’t people just use the big data centres to make and run even bigger more powerful models than they can currently support? Or massive swarms of agents to look at all different avenues of a problem?
Everyone wants radically more efficient AI. That doesn’t mean it’s coming any time soon. And when models are twice as efficient, guess what happens next. We try making one twice as big for the same cost.
Are these models harder to reason about given they produce tokens non-linearly? Especially since we rely on non-latent reasoning to know what the model is "thinking".
reply