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

I've been using bunny.net for a while and it's not bad. It has some rough edges, but it does what it's supposed to and I haven't experienced any downtime.

The main "gotcha" is that there's no free plan, it's a minimum of $1 per month, you pay for usage. In practice it's very hard to spend more than a dollar in a month.


I spend 40 euros per month, with 75% because of AI scrapers.


NATS is such a cool piece of technology that deserves more hype than it gets


Given their recentish argument with the CNCF[0] not sure how much I would trust it.

[0] https://www.cncf.io/blog/2025/05/01/protecting-nats-and-the-...


But that's the company that build the thing, which has apparently been told off by the CNCF? Seems like for once the thing functioned as it was intended to function?


I really like NATS and I agree, but im generally hesitant to use it in critical systems due to https://jepsen.io/analyses/nats-2.12.1

What is your take on this?


I still can't get over the demise of Memphis [0]. :'(

[0] https://github.com/superstreamlabs/memphis


Second for NATS.

I've deployed Core NATS as few times now at scale, including within financial trading. It's been a dream to operate.

I have limited experience with JetStream, but coming from Kafka and Rabbit MQ, it seemed nearly as featureful but also easier to maintain.


I'm building an uptime monitoring service, in Elixir, called https://larm.dev. It's a tough field because for some reason people vibe coding apps think this is very easy to do, and there are new apps coming out pretty much every day. I'm still figuring out how to effectively stand out in the noise.

I really enjoy working on the app though. The backend is Elixir, with a Phoenix LiveView dashboard. I've got a cluster of 3 nodes running, talking to each other. The probes that check the monitoring targets are tiny go binaries, spread across hosting providers across the world. I've also got synthetic probes now, running in little playwright sandboxes.

A lot of the challenges have been around how to distribute work across the probes, with different strategies for the basic TCP/HTTP probes vs the synthetic workers, and how to effectively store large amounts of events (Clickhouse).


Elixir is perfect for stuff like this, very cool project!


hey.. this looks interesting and has generous free limits. will try to give it a spin


150 euros a month to try it out is a bit rough, although I guess you're aiming for a different market than hobbyists


compacting


Yup, been running it on Hetzner arm64 for a while. No issues


Ah nice thanks for the feedback


I think maybe you've understood. The study doesn't say that all birth-assigned male brains are larger than all birth-assigned female brains. There's still variety within the group, with lots of girls with larger brains than lots of boys.


If you read the article the author does quote the US embassy in Japan strictly advising against this and that you risk arrest and deportation, that immigration officials do crack down on digital nomads, especially re-entering Japan to renew 90 day tourist visas to work.

A lot of countries have laws against working remotely without a visa, although apart from the US few actively enforce them.


Seems like the restriction would only make sense in the context of working for a Japanese company. Similar to US visas for visitors where the traveler cannot visit the US for work purposes with a US-based employer.

Otherwise, opening a work laptop and answering some work emails for your foreign employer would be risky.


Precisely this - countries protecting their job markets against foreigners working illegally (not paying taxes, undercutting wages, etc).

This has nothing to do with you working for your own foreign employer while on vacation.



They are not mutually exclusive.


"The reason Google seemed a bad idea was that there were already lots of search engines and there didn't seem to be room for another." - Paul Graham

"It already exists" is a terrible reason not to do something


The difference is that Google had a clear unique value proposition that was to provide search results (and only search results) back extremely quickly and were highly relevant when they other players were focused on creating "web portals" and did not focus attention on search.

With CodeCombat and Codeacademy there UVP is very obvious (make learning to code a game and teach to code online resp.) and had not previously been done. With this site I don't understand what the UVP is (social programming challenges?) that hasn't been already by something like TopCoder, Sphere Online Judge, etc.


"Achieve mastery through challenge" is the tagline. The idea here is to push yourself to solve problems you may have not attempted before, and to learn from others by seeing how they solved theirs. I've have personally learned a lot from seeing how other people solve problems, I even learned a lot from creative uses of solving "Hello World" which was a bit of a surprise.

In short: Codecademy is meant for those who want to learn programming. Codewars is for existing programmers who want to get better at programming.


Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

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

Search: