Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 44 min 20 sec ago

Show HN: STT-MCP – local STT for agents

Thu, 07/23/2026 - 11:06am

For when you need agents to consider the speech within an audio/video file.

Comments URL: https://news.ycombinator.com/item?id=49022848

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Local-first archive of your ChatGPT/Claude chats

Thu, 07/23/2026 - 11:05am

Capture your ChatGPT & Claude chats into a private, searchable archive you own, and sync them to Obsidian. Local-first.

Comments URL: https://news.ycombinator.com/item?id=49022840

Points: 1

# Comments: 0

Categories: Hacker News

Four Forks: AI Riskgaming Scenario

Thu, 07/23/2026 - 11:04am

Article URL: https://fourforks.riskgaming.com/

Comments URL: https://news.ycombinator.com/item?id=49022825

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Verify what an AI agent did, then tamper with the record (no signup)

Thu, 07/23/2026 - 11:01am

The current state of in-market autonomous AI is “want something done; trust that they do it”. The operation running the models hold all of the logs, and 1st party logs are inherently not the strongest. It’s: “I did my homework, I graded my homework.. my homework got a passing grade. Trust”.

Cinchor is the lightweight tool that operations can use to share verifiable records of autonomous agents’ context, instructions and output. The proofs are anchored and retrievable in a tamper-evident manner (I built a custom L1 as a substrate for this and right now I operate all of the validators. There’s zero token-exposure for the AI accountability layer, while validator independence is on the roadmap).

Looking for input from the HN community. Where is this redundant with something you already use, if so?

Comments URL: https://news.ycombinator.com/item?id=49022766

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: WatchMachineGo – A visualizer to show hardware performing LLM inference

Thu, 07/23/2026 - 11:00am

I love learning new concepts by playing around with them (think [explorable explanations](https://en.wikipedia.org/wiki/Explorable_explanation), and I got more and more interested in running local LLMs on my own hardware. Since we live in the age of "speak, and your side project will be done" (joking, but LLMs are really helpfull for me when it comes to frontend stuff and for brainstorming in general! :D) I built the tool I needed myself :)

WatchMachineGo is basically a visual simulator that simulates how a local LLM model gets loaded, prefilled and then used for inference, while showing the effects of different hardware parameters like memory bandwitch or setups like no GPU, two GPUs and so on.

All free and without ads, forever.

I plan to open source it too, but want to think about how first, still.

If you check it out: Thank you very much and I hope that it will be time well spent! :)

Comments URL: https://news.ycombinator.com/item?id=49022761

Points: 1

# Comments: 1

Categories: Hacker News

Ask HN: Does anyone have an old Goodreads API key?

Thu, 07/23/2026 - 11:00am

They shut down their API program years ago, but I was hoping to find someone who had an old key I could use.

I run BookDNA.com and it would be helpful for us. Anyone know anybody who still has a legacy key?

Comments URL: https://news.ycombinator.com/item?id=49022755

Points: 2

# Comments: 0

Categories: Hacker News

Show HN: Hosted PaddleOCR-VL-1.6 API

Thu, 07/23/2026 - 10:58am

We do a lot of document processing, and PaddleOCR-VL-1.6 is one of the best open models we've used. We wanted to use it as an api, but couldn't find anyone hosting it. so we started hosting it ourselves, but to get full utilization on the GPUs, we decided to let others use it as well.

If we did the pricing math right (which I hope we did), it should be the cheapest OCR there is, at just $0.001/page. Let us know if you find it useful

Comments URL: https://news.ycombinator.com/item?id=49022723

Points: 1

# Comments: 0

Categories: Hacker News

Pages