News for hackers. Stuff that matters.

barapa

I don't get why you built it if your plan was to finish and theN do cold outreach. Why wouldn't you test the idea before and as you built?
This article is devoid of content
If grades matter, the students will cheat.
Re:Tailwind Labs is joining Shopify on Wednesday September 09, 2026 @12:24PM (#49629078)
It shouldn't exist bc it addresses a massive inefficiency? What do you think markets are for
Re:Gemini 3.8 Flash on Wednesday September 02, 2026 @12:17PM (#49538526)
love these flash models
Re:Startup Anti-Patterns on Sunday August 30, 2026 @06:36PM (#49503513)
A startup is not the code
Re:The brain may be about to have its Ozempic moment on Tuesday August 11, 2026 @05:03PM (#49264442)
Every conceivable thing 'may be about to' happen.
Re:Ask HN: What are you working on? (August 2026) on Monday August 10, 2026 @09:18AM (#49243251)
Word game I play with my family and wife. Very addictive.
Mom, the website tricked me!
Re:Ask HN: How do you handle clients who don't pay on time? on Saturday April 04, 2026 @10:23AM (#47639326)
I find it useful to have goons on payroll that make these kinds of problems go away
Re:Nobody Gets Promoted for Simplicity on Wednesday March 04, 2026 @09:32AM (#47247913)
I promote people for simplicity
how is this a company?
Re:AI will make our children stupid on Saturday December 20, 2025 @03:12PM (#46339180)
I don't find this all that compelling. Different technologies can have different effects. And why would future effects be influenced by the accuracy of random people's predictions of other events in the past?
Re:Show HN: HN Wrapped 2025 - an LLM reviews your year on HN on Saturday December 20, 2025 @03:10PM (#46339156)
I think mine confabulated criticism of a point of view as espousing that point of view.
don't loving these
We have done a lot of work solving this exact challenge at legaide.ai. I was both sad and relieved when gemini 3 didn't deprecate our startup.
Re:The Parallel Search API on Thursday November 06, 2025 @11:32PM (#45843576)
I don't really understand this. You can and should tell the llm the source of the search results.
Re:Show HN: Butter – A Behavior Cache for LLMs on Tuesday October 28, 2025 @09:36PM (#45741601)
We often will repeat calls to try again. Or sometimes we make the same call multiple times to get multiple answers and then score or merge them.

Is this used only in cases where you assume the answer from your first call is correct?

Smart invisible regex makes it fast and prevents it from crashing? What does that mean?
I implemented copy to clipboard in datastar in maybe 1 minutes with an AI agent. What exactly are you providing to the world for free?
Re:Published a Book –> Talk Python in Production on Thursday October 09, 2025 @09:07AM (#45527179)
Chill dog
Re:Everything that's wrong with Google Search in one image on Wednesday September 24, 2025 @08:10PM (#45367591)
Yes, things change. In fact, change is basically the only thing you can confidently predict.
Re:YouTube Is a Mysterious Monopoly on Wednesday September 10, 2025 @11:37PM (#45207497)
If things disappear, that is ok. Everything is fleeting.
Imagine working for 13 years and creating something only worth 1.4B dollars. What pathetic losers
Re:An LLM is a lossy encyclopedia on Tuesday September 02, 2025 @08:26AM (#45102192)
They are training on your queries. So they may have some exposure to them going forward.
Re:Launch HN: Dedalus Labs (YC S25) – Vercel for Agents on Friday August 29, 2025 @07:54AM (#45062834)
Why does every comment start with 'congrats on the launch'?

Feels unnatural

Re:Claude for Chrome on Tuesday August 26, 2025 @03:56PM (#45031560)
I really don't like Dia. Hijacking the search bar to use their own AI model, which is just slower than google's AI mode is such a bad experience. I am happy for chrome to have built-in AI tools when needed.
Re:Everything I know about good API design on Sunday August 24, 2025 @10:34PM (#45009657)
They suggest storing the idempotency key in redis. Seems like if possible, you should store them in whatever system you are writing to in a single transaction with the write mutations.

Older »