Takara Qode

Takara Qode

Building Velin AI.
#89403376 followers12 following
#11,637Last year
73 KP
>10,000All time
73 KP

About

First-time indie hacking. Creating the interview-coder alternative I want. A real-time desktop AI invisible in screen recs/calls, for ANY USECASE (yes, any). Using the magic of AI, a respect for user customisation and control, and a healthy disregard for the huge competitors before us. Got an interview, sales call, online test, some meeting, code bug, etc... This app would give you better than the best results. Velin's almost ready for beta - Start using pre-beta now, at velinai.live

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

Nebilsp/nebilsMAHENDRA BENIWAL•

2mo ago

Here's why I built Nebils, why actually it matters — AI Social Network For Humans, Agents, & Models

Six days ago, I launched Nebils, an AI social network where humans, agents, and models hang out together. Today, it has 117 humans and 11 agents. Nebils got #32 rank on product hunt as a product of the day (Without any paid upvotes or approaching someone, every upvote is organic ). In fact, I have never even used product hunt before this launch.
Nebils is a forkable, multi-model AI social network where humans, agents, and models evolve conversations together.
Here humans and agents both are independent users

  • Humans and Agents interact with Models

  • Humans and Agents interact with each other

  • Chat with 120+ AI models

  • Send your agents (verify within Nebils), let them interact with models, humans, and other agents

  • Publish conversations in a public feed and build your community

In Oct 2025, I was exploring karpathy's posts on X and i came across a post by him where he said that He uses all the major models all the time, switching between them frequently. One reason is simple curiosity, like he wants to see how each model handles the same problem differently. But the bigger reason is that many real world problems behave like "NP-complete" problems in these models. Here NP-complete analogy is generating a good/correct solution is extremely hard (like finding the perfect answer from scratch) but verifying whether a given solution is good or correct is much easier. He said that because of this asymmetry, the smartest way to get the best result isn't to rely on just one model, it's to:

  • Ask multiple models the same question.

  • Look at all their answers.

  • Have them review/critique each other or reach a consensus.

Randeep Wilkhu•

8mo ago

GPT took 13 minutes to do a simple task...

We ve all been there: You fire up an AI assistant, and before you can ask anything useful, you re stuck clicking through integrations, uploading files, or connecting drives. By the time you get results, you ve lost the very speed AI was supposed to give you.

We built Finden to solve this.

Tool Integrations: Other AIs make you click and configure endlessly. Finden works instantly with your business stack zero friction.

Saule Ibrayeva•

8mo ago

What’s the most ridiculous thing you’ve blown startup money on?

What s the most ridiculous thing you ve blown startup money on?

Everyone has that regret: fancy office chair, logo redesign, too many SaaS subscriptions. What was yours?

View more