Hacker Newsnew | past | comments | ask | show | jobs | submit | skadamat's commentslogin

Definitely vibe coded. It follows the same generic Claude UI patterns for a data app / data oriented website. Not necessarily a bad thing per say if it's still curated and tweaked with human taste. And ofc validated to work :)

Hi @skadamat - I am not very experienced with claude code and don't know what it has done previously but new opus 4.6 is great. I think I need to work on claude.md. That really seems to be the soul of Claude. I've incurred quite a lot of money on API cost and claude plan and my time. But I feel like that can be cut to 1/4th easily with a solid claude.md plan.

Speak for yourself :) Weather data is already freely available.

I want something that integrates into my life very minimally and just gives me the information I need when I need it. Most weather apps fail at this.


Couldn't agree more! This is why I wrote the Eulogy for Dark Sky: https://nightingaledvs.com/dark-sky-weather-data-viz/

I read this a bit ago and really enjoying it! It felt like it did justice to the effort that people wouldn't appreciate otherwise.

I reference this often! Thanks for writing it.

My understanding is that they're just starting out with the app. Someone posted it to HN prematurely. Dark Sky expanded to support global weather and I'm sure Acme will as will.

Congrats on the launch! How do you guys compare with Datalab with regards to accuracy?

https://www.datalab.to/


I want to know this, too. Lots of these companies are doing the same thing, but leave out benchmarks that include marker


Thanks! We have a lot of respect for the work VikP and his team did on Surya but we haven't benchmarked his newer pipeline so I don't want to make a 1:1 claim.

If you want to do a side by side with your use case we'd be happy to set you up with free trial access.


I want to test side by side with them and my own pipeline - can you set me up with trial access please? Thanks


I would love a Genius.com / annotation layer on top of these bills too. Just a dream I'm sharing out loud for no particular reason :) love govtrack in general otherwise!


Without commenting on the merits of that idea, I'll just say that I do not want to be the one who has to moderate user generated content.


Only if it is shared annotations is it a problem.

It need not be shared , think more like a public notion/ share point document with comments visible . I.e experts(users) can create their own individual annotated versions and share with others .

As long as there is no single version of the annotations , moderation is not needed


I think the issue is that a person reading without an interlocutor has a better chance of getting some truth from the sum of the bill than reading with an “expert” bent on swaying them towards a fringe interpretation or even directly lying to distort the content. The feature lets them put on an air of factuality but really just inveigle people with a chopped take on a document.


Honestly it makes sense and resembles how other companies pay sales people. Lower base salary than other roles in the company for similar years of experience (roughly) but with a commission component that's some percentage of each sale. Commission is a big big part of sales culture that I suspect is hard to eliminate in an effort to be different.

What's interesting is that often times the commission has no cap, so top sales people can take home higher income than even than executives (at least in cash compensation).

But to the commenter's point, true transparency would share the commission % as well :)


The challenge of syncing from stubborn SaaS tools to your data warehouse / database I suspect is different than syncing data from your data warehouse / database back to SaaS tools. Specifically, reverse ETL has to incorporate more context from the business I guess so the data that lands in the 3rd party tools is actually solid.

Once you have customers and a good network of integrations with a large number of tools, I suspect it's easier to just buy that company than build it all yourself?


This is exactly right. We even went so far as to build a proof of concept internally, and the technical challenges are just very different. The simplest way to explain it is that Fivetran connects a skinny pipe (APIs) to a fat pipe (databases) while Census connects a fat pipe to a skinny pipe.


The data is only as solid as you make it to be. Ultimately reverse ETL is just a technology (basically from SQL to APIs). The quality/correctness of data is someone else's headache. I've been there and done that, and reverse ETL is a feature-product with huge churn. See how Hightouch pivoted hard from that into CDP.


There seems to be some content previews here: https://typefully.com/DanHollick


Lovely website! I stumbled into this other account by the same author that showcases some of the work that might end up in this 'book':

https://typefully.com/DanHollick


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: