I use Waymo's all the time. There are still some quirks they need to figure out and polish the experience, but it really is happening and it appears that Uber's head is in the sands or I'm missing something here.
5,887 karma · joined July 5, 2010
[ my public key: https://keybase.io/emilsedgh; my proof: https://keybase.io/emilsedgh/sigs/o8NMyYnVffMkRTHjiNnCtvSnswvOxnD9ykbt7GI3rKU ]
hnchat.com:AQAD4YPRs8sNjUSoCZy8
I use Waymo's all the time. There are still some quirks they need to figure out and polish the experience, but it really is happening and it appears that Uber's head is in the sands or I'm missing something here.
LLM's are brains with no tools (no hands, legs, etc).
When we use tool calling we use them to empower the brain. But using normal API's the language model providers like OpenAI have no access to those tools.
With MCP they do. The brain they create can now have access to a lot of tools that the community builds directly _from_ llm, not through the apps.
This is here to make ChatGPT/Claude/etc _the gateway_ to AI rather than them just being API providers for other apps.
But, it appears that we are hitting our limits at this point. We have a table with tens of millions of rows and the use case is that it's faceted search.
Something like Zillow, with tends of millions of listings and tens of columns that can be queried. I'm having a tough time scaling it up. Does anyone have experience building something like that in pg?
https://github.com/gliderlabs/herokuish
Something like this + Procfile support should allow you to gobble up Heroku customers [like us] quickly since they've been stagnating for long, no?
> Their audience has always been, and will always be application developers who prefer to do nothing low-level. How did they forget this?
to this:
Their audience has always been, and will always be application developers who prefer to do nothing except to build their main product.
> Our primary DX is a CLI. One of our defining features is hardware isolation. To use us, you have to manage Dockerfiles. Have you had the experience of teaching hundreds of Heroku refugees how to maintain a Dockerfile? We have had that experience. Have you ever successfully explained the distinction between "automated" Postgres and "managed" Postgres? We have not.
I'm pretty much sure an application developer in this day and age has to know all of them, yes. Just like git.
One end is PaaS like Heroku, where you just git push. The other end is bare metal hosting.
Every option you mentioned (VPS, Manages K8S, Self Hosted K8S, etc) they all fall somewhere between these two ends of the spectrum.
If, a developer falls into any of these "groups" or has a preference/position on any of these solutions, they are just called juniors.
Where you end up in this spectrum is a matter of cost benefit. Nothing else. And that calculation always changes.
Those options only make sense where the cost of someone else managing it for you for a small premium gets higher than the opportunity/labor cost of you doing it yourself.
So, as a business, you _should_ not have a preference to stick to. You should probably start with PaaS, and as you grow, if PaaS costs get too high, slowly graduate into more self-managed things.
A company like fly.io is a PaaS. Their audience has always been, and will always be application developers who prefer to do nothing low-level. How did they forget this?
I had to sign stuff like this and the lawyers I was sent to seemed they didn't really have much relevant experience and I'm deeply uncomfortable with their assessments given how confused they looked.
> Perhaps more importantly, this is also a strategically worrisome direction to go in, because it plays into the narrative that Big Tech is more powerful than sovereign nations.
I don't buy it. I think it can be a fantastic win for them. Announce a leave date unless the government backs down and advertise it heavily on TV and everywhere:
Your government wants us to spy on you. We are not going to comply. Call your parliament members to <blah>.
This would make them champions of privacy and every other government will know how deep their commitment is.
Rechat is the leading AI-powered operating platform for real estate brokers and agents. Think Shopify for real estate—a mobile-first super app with marketing automation, workflow management, and everything agents and brokers need to run their business in one place. We’re a small, sharp team building a big, sophisticated product without the usual corporate nonsense.
Why You’ll Like It Here:
Remote-first with flexible hours
Minimal meetings—we focus on real work
No tech hype-chasing—we use the right tools, not the latest trends
Flat team structure—no layers of bureaucracy
Who We’re Looking For: Senior Frontend Engineer (TypeScript, React) – Own the UI and craft intuitive experiences
Senior Backend Engineer (Node.js, PostgreSQL) – Build and refine our robust, high-performance backend
If you thrive in small teams solving big technical challenges, reach out to emil+hn@rechat.com.Duh. You guys have completely forgotten who your audience is. Your audience is _application developers_. I have no idea what all that mambo jambo means in that article _and thats why I pay Heroku_.
I'm on Heroku because I don't want to know about cloud native and fir and open telemtry are. You tell me I should get excited on Heroku? How about improving your autoscaling options so the narrow response-time-based scaling is not the only option?
All that article tells me is that you guys are maybe improving your underlying infrastructure. Meh. Good for you. From a customer (AKA Application Developer) perspective nothing has changed.
And no, I don't have stock and I was very skeptical of them being able to crack this but I was proven wrong in the past 2 months.
I've always been skeptical [of self driving] but at this point (after having a few rides with Waymo) it appears that the folks at Alphabet have figured it out already and are coming for Uber. Why is not that affecting Uber's price?
Other web pages don't have such access.
Their moat right now is developer tooling. They allow fine tuning + an easy API to use their llm.
Noone else does that right now. By the time others do, so much tooling and infrastructure has been built around OAI that the switching costs will be a lot.
It will get to the point that if you want your llm to beat oai on the market it won't be enough that you are as good or even better. You need to be vey very significantly better than OAI. For an extreme example of this see Windows. The network effects keeping it together are so strong that the platform becoming an abandoned adware hasn't been enough to push users to significantly better platforms like Mac.
Now I've fine tuned the hell out of gpt-3.5 and I'd love to see how my app would performed on a fine tuned Opus. I went to their website and I can't seem to fine tune their model yet. Meh. My guess is that by the time they make it available I won't have a strong reason to even try anymore.
1. You can go to System Settings -> Keyboard and there, enable Super key to act as another button.
2. Set the shortcut to that another button.
The main reason is langsmith. (But there are other reasons too). Because of langchain we got "free" (as in no development necessary) langsmith integration and now I can debug my llm.
Before that it was trying to make sense of whats happening inside my app within hundreds and hundreds of lines of text which was extremely painful and time consuming.
Also, lc people are extremely nice and very open/quick to feedback.
The abstractions are too verbose, and make it difficult, but the value we've been getting from lc as a whole cannot be overstated.
other benefits:
* easy integrations with vector stores (we tried several until landing on one but switching was easy)
* easily adopting features like chat history, that would've taken us ages to determine correctly on our own
people that complain and say "just call your llm directly": If your usecase is that simple, of course. using lc for that usecase is also almost equally simple.
But if you have more complex use cases, lc provides some verbose abstractions, but it's very likely that you would've done the same.