This is very cute. I don't think I'd ever thought of having a cellular automaton where there's some global state that can change that influences the local cell rules. Would be interesting to add more control/energy variables like for collecting resources/food.
Yes I hope in the future we can get to what OCaml 5 has with their algebraic effects system, and hopefully fix any flaws we see in there, so that async will just be syntactic sugar over the underlying effects system.
The thing is that this argument doesn't work with Go because its type system (and the whole language, really) is much less expressive and compiler gives a lot less feedback to the LLM. So it tends to have to write more unit tests and do more cycles of testing (and spend more tokens) to get it right.
The argument about type system is absurd anyway. The types in a program aren't a universal vocabulary that the LLM would already know about like the words of English language. They are unique to each program and domain so an LLM can't be better at it.
Let me elaborate further - it's like the proficiency of LLMs in writing English vs writing Sawahili or Kurdish.
The types of a program are like Swahili or Kurdish etc even worse because those languages still have sizeable chuck on the Internet and digital archives but types of a program are very specific to it.
Studies have shown that natural human languages are all more or less equally expressive in terms of bits per second while speaking. There's lots of different ways they can be structured but they tend to follow common rules that have been well-characterized by linguists. They can be used to describe formal mathematical statements, but are not rigorously formal languages themselves.
Programming languages, in contrast, are constructed and vary much more in their designs. They are formal languages, making them closer to math than spoken language. LLMs being able to describe concepts more thoroughly and precisely through more expressive semantics obviously makes some languages more suitable than others.
The type system of a language is just one aspect of it that allows the language to provide guarantees to the LLM (and the user) about correctness of the code it's writing.
I am not speaking about specific types in specific programs. I am talking about the ability to describe complex constraints that LLMs (and humans) end up using to make writing correct code easier and more productive. Some programming languages absolutely are more effective at this than others, and that's always been true even before LLMs.
Facebook ran experiments on on unknowing teenage girls to study how being shown negative content leads to negative mental health outcomes, which has lead to suicide.
I hope there's some forced migration of the SaaS business model towards primarily being "just an API" for whatever magic sauce it is they have. Too much of SaaS moats are just locking the backend behind an undocumented API.
Users should be able to have full control over their experience interacting with third parties if they want it. This isn't unique to post-LLM stacks like this, but it seems like this shifts the balance of power.
The next step after injecting custom UI controls is to build completely alternative frontends. The next step after that should be to build generic local frontends that abstract over multiple comparable thirdparty providers.
First, is a 500 because you are using the API in a way that is unexpected a customer found defect? If Claude can't find the answer, what is the expectation of support?
If an internal team makes a change that breaks your workflow (because it was an unexpected use case), is that a CFD?
Do teams slow down in new features because the API must be the stress test of a public api?
I'm fine with unsupported frontends but an external API will be very difficult to keep static.
The last company I worked for before going into consulting full time was a startup where I was the then new CTOs first technical hire. The company before then outsourced the actual technical work to a third party consulting company until they found product market fit.
His primary mandate was API and micro service first.
Our customers were large health care systems.
We had a customer facing website that was built on top of the same APIs that we sold our customers.
Our customers paid for the features they wanted and those features were available on our website, they were used for their website and mobile apps and the ETL process was either via a file they sent us and we ran through the same APIs or they could use our APIs directly for both online and batch processes.
This is no different from the API mandate Bezos made at Amazon back in 2000.
You don’t have to keep an API static - that’s what versioning is for.
I think the talking point is maintaining a well versioned and solid API as product is way harder than shipping a few screens that can change whenever you need them to. (behind those screens being a bunch of duct tape to a clusterF of internal APIs). no guarantees.
what you're saying is that you were at a company that did that hard thing of shipping APIs as product.
Nice vision, "alternative frontends" is something really useful for horizontal SaaS. We do this for over 2000 customers, from field workers to CEOs of public companies, and it's so satisfying to hear the great feedback when they tell me that they finally have software perfectly adapted to their workflows.
If attention-span was shot with social-media, it has no chance in the age of AI. All these deep tech-tools potentially have tons of value, but if it doesn't make sense in 5 seconds, very hard to compete.
I think the right step would be to somehow communicate to the vendor that this feature is needed (eliminating the PM backlog BS) and their coding Agents should pick it and build it. The real moat they have is SaaS vendors have everyone believe that trivial feature requests take time to implement.
> have everyone believe that trivial feature requests take time to implement.
This could not be more wrong. Features do, because telling a user they can do X comes with a standing promise that it works, the results are correct, the ui is accessible, the feature cleanly interacts with all other features in the system (both now and in the future), corner cases are worked out, etc. And that burden is where prod+eng spend time.
There is an entire industry of Salesforce, Workday, ServiceNow consultants and almost any other major SaaS app that you can hire to customize the app based on public APIs. I can’t imagine choosing any mission critical SaaS app without publicly documented APIs
That introduces a level of indirection between "what I want" and what gets built. A workflow like the OP just has less friction. SaaS platforms would want to provide more stable accessible APIs if it becomes a popular model, because users would find it more usable.
these embeddable UI could be a direct ask on how users want a workflow, the SaaS vendors can distribute the embeddable UI and see if it clicks with a lot of users. Would push them to create a stable API
Surprised this is your take coming from a UX designer. You think a straight path for every user to add their feature ideas results in a good UX?
edit: reading further into this, the idea is perhaps that users vibe-code their own distinct UX with everything valuable to them. That's not a bad take, but even in that world, I wouldn't think UX and product disciplines become exposed for having no value at all.
My take in this (ironic) comment was just "no feature is free", which I don't think should be odd coming from a UX designer!
> the idea is perhaps that users vibe-code their own distinct UX with everything valuable to them
I do find this interesting. I work on a complex business operations and reporting platform and every facility has their own lil quirks. More control in their hands would let them smooth out their workflows while still relying on the foundational work our platform does.
Ah, I didn't register the sarcasm. Typical HN, it's probably why you're downvoted.
Yes, today's HN session has me nerd-sniped about what the future of product development looks like. I've been thinking how mock-to-prototype is just too slow when engineers can ship so much so fast. Eng needs design direction especially when it's too easy to "solve design" with tailwind components and "You're a designer from a top saas company" prompts.
But what if the new UX is less visual-first and more IA, primitives and well structured object models... now that has me thinking.
reply