valianter
Re:The Infinite Game
on Wednesday August 19, 2026 @09:44AM (#49361518)
Wrote this small blog on how it has been to run my YC startup. Lots of learnings about myself since this is my first job
Re:Show HN: Prism – Let browser agents access any app
on Thursday September 25, 2025 @03:38PM (#45377896)
Does this solve Captcha? Or is this only for people who are trying to maintain browser sessions in very niche use cases. Pen Testing is cool but I feel like the main use case is by allowing agents to work across the web on any website.
Re:Show HN: Airweave – Let agents search any app
on Monday May 12, 2025 @12:59PM (#43965140)
Is chat always the best interface for all of these apps? I feel like search is the natural first step, but chat-based search has been around for a while. Feel like an MCP-based version of Glean/Onyx/Moveworks/Dashworks is interesting, but unsure how much better it makes the product. Curious to see why your product is better
Perplexity Launching Agentic Browser
Is Perplexity Dead?
OpenAI has finally released their long-anticipated search feature. I'm curious to hear about people’s experiences with it and whether it offers any significant advantages over what Perplexity provides for free.
Re:Launch HN: Haystack (YC S24) – Visualize and edit code on an infini...
on Wednesday September 25, 2024 @12:33PM (#41649178)
I get that this is a completely new idea so adoption is going to be slow but I'm curious to see how your user interviews and user research is going. I'm a young dev but I'm not even sure if I would use this because the way I've learned to code is already so ingrained into the traditional IDE. Nevertheless, congrats on the launch!
Re:United Nations says global AI fund needed to help developing nation...
on Thursday September 19, 2024 @06:20PM (#41596943)
Is there a big enough "Internet access" fund by the UN yet? I feel like AI is a fun word but how can AI be accessed without the original building blocks needed?
New Free Mistral API Tier and Vision Capabilities
Ask HN: To what extent is PMF a function of good marketing
When listening to YC videos or general startup talk online I see the idea that you know you have Product Market Fit when you feel an overwhelming amount of growth that you can’t handle.The Stripe founders said they knew they had it when a customer sent them brownies to get off the waitlist for a feature. Obviously, Stripe had built an amazing product that resonated with users but how much of...
Show HN: Open-sourced AI for enterprises by Vanderbilt
https://www.amplifygenai.org/#FAQ
I'm not the author of this program nor do I have any stake in it, but I just thought I'd show off a project coming out of my university.
Open Sourced alternatives to SaaS products [video]
Ask HN: Have you made the switch to an AI code editor?
I've been seeing news about all these AI co-pilots/code generators and I'm wondering if anyone has actually made a full time switch for >1 month.Extensions like Coedium and co-pilot are fairly easy to install and use but I've been hearing about Zed and Cursor a lot. Is anyone actually using these products or is it just more hype.
Re:Show HN: LLM-Term – Simple Rust-based CLI assist tool
on Thursday August 29, 2024 @10:59AM (#41391476)
Really like this! What did you use for the demo?
Ask HN: Isn't all SaaS just wrappers?
I'm not sure if I can think of any SAAS product that isn't another wrapper or abstraction around code, database, another service etc... I just don't understand why people seem so upset about these new companies being GPT wrappers.SAAS brings the cool things people build in our insular computing community to the general user in an intuitive way, and that's celebrated. Not sure why these "GPT...
Re:Inference is free and instant
on Tuesday August 27, 2024 @11:22AM (#41368575)
> No matter how fast Searle is, he won't be able to come up with a beautiful and original Chinese poem that has the creative spark special to humans.
This analogy seems flawed to me. Searle is in an empty room but LLMs are not. They are constantly learning from user inputs and data is continuously being made more available for LLM ingestion. I still don't think that an LLM will completely replace humans at pure creativity but I don't see why it can't come close. Especially since we're only 2 years in to this craze.
Re:
on Thursday August 22, 2024 @11:02AM (#41321106)
I learned web development while Supabase was the de facto standard for most hobby projects. However, I used Firebase and it seemed pretty easy to use.
I realize that Supabase is supposed to be the open-sourced Firebase, but is that the only reason? While the Firebase UI isn't as "sleek" as Supabase, but I'm not convinced that it's enough to beat a giant like Google. I'm pretty new to the open-source and hobby computing world; would love to see everyone's perspective.
Re:Show HN: If Twitch had actual channels
on Thursday August 15, 2024 @11:29AM (#41257213)
Is this a fork of the YouTube project
Re:Show HN: Free Online Open Graph Generator
on Thursday August 15, 2024 @11:28AM (#41257199)
This is so cool! OG images are the worst to make
Re:Ask HN: How do companies still justify LeetCode
on Tuesday August 13, 2024 @10:49AM (#41236032)
What about during live interviews though? Not sure if I see the justification for DSA interviews there anymore
Ask HN: How do companies still justify LeetCode
As ChatGPT gets better at solving technical interviews I don’t understand why companies still insist on giving Leetcode style problems in their online assessments.I get that they need to cut a large amount of people before live interviews but hackerrank/code signal have the ability to test “real world” scenarios like debugging,sys design,using APIs,etc…In live interviews I feel like DSA...
Re:Rise of the New York Tech Scene
on Thursday August 08, 2024 @10:30PM (#41198351)
I'm curious to see the types of founders in NYC vs. SF. Is it true that the NYC founders are more "worldly" and "human"??
LangChain Is a Black Box
I've been working with Langchain to develop a POC and when I try to understand the bugs in my code I feel like I am going down this huge rabbit hole of code. Every time I click into a piece of code there are 10 more places that I have to look that MIGHT be the source of the bug.I get the idea that things should be abstracted away and that's the point of a library but this feels like a little much.
Re:Show HN: I accidentally built a cheaper Glean
on Monday July 29, 2024 @12:38PM (#41101709)
Oh shoot! Didn’t know that I’ll delete the post and just put the GitHub demo. Thank you!
Show HN: I accidentally built a cheaper Glean
Hi!I built Atlog without knowing what Glean was, but I realized that Knowledge Management is a pretty common problem for companies! However, I wanted to take a bit of a new approach so Atlog does a couple of things differently...1. We are going to offer token based pricing so anyone can try it out without talking to sales2. We are more focused on trying to extract and store tacit knowledge...