HNHacker News
TopNewBestAskShowJobs

barapa

162 karma · joined December 4, 2010

submissionscomments
barapa··on How I changed teaching after AI managed to do all my homework assignments
If grades matter, the students will cheat.
barapa··on Shopify acquires Tailwind
It shouldn't exist bc it addresses a massive inefficiency? What do you think markets are for
barapa··on Gemini 3.8 Flash
love these flash models
barapa··on Startup Anti-Patterns
A startup is not the code
barapa··on The brain may be about to have its Ozempic moment
Every conceivable thing 'may be about to' happen.
barapa··on Ask HN: What are you working on? (August 2026)
Word game I play with my family and wife. Very addictive.
barapa··on Ask HN: What are you working on? (August 2026)
https://wordknots.barapa.dev/
barapa··on Ask HN: How do you handle clients who don't pay on time?
I find it useful to have goons on payroll that make these kinds of problems go away
barapa··on Nobody gets promoted for simplicity
I promote people for simplicity
barapa··on Launch HN: Omnara (YC S25) – Run Claude Code and Codex from anywhere
how is this a company?
barapa··on AI will make our children stupid
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?
barapa··on Show HN: HN Wrapped 2025 - an LLM reviews your year on HN
I think mine confabulated criticism of a point of view as espousing that point of view.
barapa··on Two recently found works of J.S. Bach presented in Leipzig [video]
don't loving these
barapa··on Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark
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.
barapa··on The Parallel Search API
I don't really understand this. You can and should tell the llm the source of the search results.
barapa··on Show HN: Butter – A Behavior Cache for LLMs
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?

barapa··on Show HN: Scriber Pro – Offline AI transcription for macOS
Smart invisible regex makes it fast and prevents it from crashing? What does that mean?
barapa··on Datastar: Lightweight hypermedia framework for building interactive web apps
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?
barapa··on Talk Python in Production
Chill dog
barapa··on Everything that's wrong with Google Search in one image
Yes, things change. In fact, change is basically the only thing you can confidently predict.
barapa··on YouTube is a mysterious monopoly
If things disappear, that is ok. Everything is fleeting.
barapa··on An LLM is a lossy encyclopedia
They are training on your queries. So they may have some exposure to them going forward.
barapa··on Launch HN: Dedalus Labs (YC S25) – Vercel for Agents
Why does every comment start with 'congrats on the launch'?

Feels unnatural

barapa··on Claude for Chrome
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.
barapa··on Everything I know about good API design
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.
barapa··on Build durable workflows with Postgres
Agree on the UI - I wish it was improved
barapa··on Gemini 2.5 Deep Think
I am not seeing this llm serve command
barapa··on Gemini 2.5 Deep Think
Available via API?
barapa··on Launch HN: Lucidic (YC W25) – Debug, test, and evaluate AI agents in production
Excited to try this
barapa··on Show HN: I built an AI that turns any book into a text adventure game
Are you fetching the book content? Or just relying on the LLM to know the story?
Page 1 of 3Next →