The market is more unpredictable than it’s been in a long, long time so I hesitate to make a firm prediction but to me the odds that SpaceX will be a successful IPO over a 3-6 month window are significantly lower now. S&P inclusion basically requires funds to hold a position by default, and per their own estimates $20tn of assets are indexed/benchmarked to the S&P.
Anthropic's annualized run rate is >$40b according to outside reporting. AWS hit that by Q4 2019. There were still debates on public cloud vs on prem at that time, but by late 2019 public cloud had facilitated the creation or adoption of entire categories of software within SaaS and PaaS, not to mention consumer internet businesses like Uber and Airbnb. The net impact of AI coding tools is far more ambiguous in comparison.
The profitability comparison is fraught but worth noting that by then AWS was already extremely profitable.
I'm wondering if companies are 'diverting' engineering resources from core products to AI products with the view that the former are legacy. Kind of two sides of the same coin though.
Late last year I tried asking ChatGPT to summarize a collection of 10 researchers' views/findings on a topic and provide representative quotes. It initially looked plausible but when I checked the links, the quotes were from clearly AI generated summaries of actual interviews. The paraphrasing was also plausible but subtly and profoundly incorrect.
I haven't tested this again on the latest models though, so not sure if there's been an improvement.
This article seems to fundamentally misunderstand what 'enterprise IT' is all about (enterprise IT being different from IT for a tech-native).
IT is a highly dynamic system, and enterprises optimize for a minimal set of capabilities at the maximum level of abstraction under high levels of uncertainty and different inherited states.
This results in decisions that may not appear technically optimal but which are still an optimal outcome under the extreme uncertainty that an 'enterprise' operates in vis a vis technology paradigms.
Add to this that there is no one technology operating model. everyone has a different starting point, different inherited technical debt. They are optimizing to their own starting point, not a clean slate.
This is what people don't get about what Microsoft actually does - it abstracts both at the technical level and the operational (contracting) level. This is valuable for an organization whose core competency is not technology, even if it does not lead to the most optimal outcomes from a pure technology perspective.
It is possible to question the sustainability of the AI buildout and not have a dogmatic position on AI development.
There are still major unanswered questions here. For instance, all of the incremental data capacity build out is going to businesses that have totally unknown LT unit economics and that today are burning obscene amounts of cash.
More like he wants to ban accelerator chip sales to China, which may be about “national security” or self preservation against a different model for AI development which also happens to be an existential threat to Anthropic. Maybe those alternatives are actually one and the same to him.
Chip costs strongly impact the economics of model serving.
It is entirely plausible to me that Opus 4.7 is designed to consume more tokens in order to artificially reduce the API cost/token, thereby obscuring the true operating cost of the model.
I agree though, I chose poor phrasing originally. Better to say that GB200 vs Tranium could contribute to the efficiency differential.