News for hackers. Stuff that matters.

lyime

Lol been thinking about this for the lat few months. Good to see someone build it.
Only *half of Google's revenue is generated outside of the US.
You just proved my point.
Re:Tell HN: Happy Fathers Day on Sunday June 21, 2026 @07:20PM (#48623630)
When I was growing up, I watched my dad fix many things around the house. He took it on as a challenge, but you could tell he was genuinely curious about how things worked.

Taking something apart and trying to fix it was his way of figuring it out. I really appreciated that, and I find myself operating in similar ways.

He also had a fearless approach and the belief that he could fix it. I never saw him give up on a project—almost to a fault. There are areas for improvement in that approach, like asking for help.

Thanks, Dad, for inspiring me to fix things, take on challenges, be fearless, and believe I can succeed if I applied myself.

To all dads out there. Happy Father's Day.

I wrote this as I was motivated to fix my espresso machine last week https://x.com/dodeja/status/2068170135911981068

You underestimate how large the US market is.
How is this different/better than charles proxy/proxyman or similar apps?
Re:Is anyone actually using OpenClaw? on Wednesday April 15, 2026 @06:20PM (#47786092)
raises hand
Re:I still prefer MCP over skills on Thursday April 09, 2026 @11:40PM (#47713330)
auth
Re:Glaze by Raycast on Wednesday March 04, 2026 @06:14PM (#47255333)
Moat? Maybe they built something they wanted?
Re:OpenClaw – Moltbot Renamed Again on Friday January 30, 2026 @10:06AM (#46825228)
Read about hearbeat, that makes openclaw different than claude code.
Re:BYD Builds World's Fastest Car on Monday October 06, 2025 @12:14AM (#45487584)
China subsidies Byd. It would be bad for american car industry. So if US wants to create a fair competition, they would need to use tariffs or subsidies the US car industry players that could compete fairly with BYD.

Looks like US is using tariffs to compete.

Re:Claude's memory architecture is the opposite of ChatGPT's on Thursday September 11, 2025 @04:49PM (#45215975)
How do you define "LLMs don't understand concepts"?

How do you define "understanding a concept" - what do you get if a system can "understand" concept vs not "understanding" a concept?

Re:Dropbox Paper mobile App Discontinuation on Tuesday September 09, 2025 @03:09PM (#45187146)
notion ate there lunch
> 1. Invite [email protected] to your product. You can send multiple invitations based on distinct roles.

this is clever

Re:How and where will agents ship software? on Wednesday July 16, 2025 @06:00PM (#44587267)
Have you tried Convex?
Are you sure? Couldnt you just just go back to the LLM if the script breaks? Pages changes but not that often in general.

It seems like a hybrid approach would scale better and be significantly cheaper.

Good hire.
I would love to automate our Youtube channel videos and transcribe with speaker identification
Re: on Friday April 11, 2025 @01:26PM (#43656263)
Lots of founders go through this. You should have an honest conversation with your co-founder. Probably couples therapy. One option is to do it with another founder who has been there (me).

You both are going through a challenging time. Of-course you are going to find some things that are more interesting to you than your founder, and vice versa. Especially if you are pivoting every month (which is a whole different problem).

Going through tough times can build resentment, the way to get on the same page is to talk.

You are not getting more than $25 of value?
It seems fair for them to train on how people use their tools, so they can make the tools better for people who use them?
Great to see people trying to solve hard problems!
Pricing? Whats bespoke about it? Whats your pricing metric?
Re:Uchū · the color scheme for internet lovers on Sunday February 16, 2025 @08:59PM (#43074112)
I did not mind it.

Nudges can be helpful.

Do the same rules apply to the government entities luke law enforcement and security services?
To your last point -- Humans make mistakes too. I asked my EA to order a few things for our office a few days ago, and she ended up ordering things that I did not want. In this case I could have wrote a better prompt. Even with a better prompt she could have ordered the unwanted item. This is a reversible decision.

So my point is, that while you might get some false positives, it's worth automating as long as many of the decisions are reversible or correctable.

You might not want to use this in all cases, but it's still worthwhile for many many cases. The use case worth automating depends on the acceptable rate of error for the given use case.

This is an impressive tool. I especially like the observability around the workflow and the steps it takes to achieve the outcome. We are potentially interested in exploring this if we can get the cost down at scale.
Re:Nvidia-Ingest: Multi-modal data extraction on Friday January 10, 2025 @01:52PM (#42658725)
So who is going to deploy this and turn this into a service/API?
Absolutely not. While that might sound like a safety feature it can also be extremely unsafe.

Imagine letting a passenger in a car use the e-brake at any time.

It's a tricky problem.

Reasonable to make a request. Also reasonable for it to be denied.

Older »