Hacker News: nastrofa

What is an Audio Decision Model?

nastrofa — Sat, 17 Oct 2026 15:56:54 +0000

Article URL: https://tazolabs.com/blog/what-is-an-audio-decision-model

Comments URL: https://news.ycombinator.com/item?id=50132207

Points: 2

# Comments: 0

New comment by nastrofa in "Speculative tool calling: cutting voice AI agent latency"

nastrofa — Tue, 13 Oct 2026 11:32:20 +0000

Have you tried the model ?

New comment by nastrofa in "Startups USUALLY start, in 12 steps ... and why they shouldn't"

nastrofa — Tue, 13 Oct 2026 09:25:05 +0000

0.5 dropsout to build on an idea they got on an acid trip

New comment by nastrofa in "We checked 495 AI product photos against the originals; 35% of errors were text"

nastrofa — Tue, 13 Oct 2026 09:17:09 +0000

slop alert

New comment by nastrofa in "DishwasherBench – Can Frontier Models Stack a Dishwasher?"

nastrofa — Tue, 13 Oct 2026 09:15:52 +0000

This is so cool!

Imagine creating real simulated env for every physical task and using RL to train robots. That will be a game changer.

Has anyone tried using Hyperframes?

nastrofa — Sun, 03 May 2026 07:14:38 +0000

Article URL: https://github.com/heygen-com/hyperframes

Comments URL: https://news.ycombinator.com/item?id=47994268

Points: 2

# Comments: 1

New comment by nastrofa in "When generative AI makes mistakes, are they the same as human errors?"

nastrofa — Sat, 02 May 2026 12:34:09 +0000

I think AI and humans operate very differently

If a human doesn't know an answer, they will either not fake it or will give a brief response to the best of their knowledge. They don't know what they don't know.

If an AI doesn't know the answer, it will find connections in its vast training patterns to hallucinate a response.

Humans think and use logic AI predicts and finds the most probabilistic answer

New comment by nastrofa in "Show HN: Large Scale Article Extract of Newspapers 1730s-1960s"

nastrofa — Sat, 02 May 2026 12:23:29 +0000

It would be really cool to create different analysis across the time

- Each month's / year's top news headline

- Left / Right swings of publishers

New comment by nastrofa in "A New Mental Model for Work in the AI Age"

nastrofa — Sat, 02 May 2026 12:18:19 +0000

A challenge I am facing is sycophant nature of LLMs. It just validates my thoughts and never questions it, can't trust it when its appreciating or supporting me.

New comment by nastrofa in "Spirit Airlines canceled all flights and is going out of business"

nastrofa — Sat, 02 May 2026 12:14:22 +0000

Good news for Frontier it seems