Hacker News: chown

AI Workflows Need Provider Escape Hatches

chown — Tue, 28 Apr 2026 09:02:45 +0000

Article URL: https://rawsignal.xyz/posts/ai-workflows-need-provider-escape-hatches/

Comments URL: https://news.ycombinator.com/item?id=47932038

Points: 2

# Comments: 2

New comment by chown in "Open models by OpenAI"

chown — Tue, 05 Aug 2025 17:18:22 +0000

Shameless plug: if someone wants to try it in a nice ui, you could give Msty[1] a try. It's private and local.

[1]: https://msty.ai

New comment by chown in "A new PNG spec"

chown — Wed, 25 Jun 2025 16:49:47 +0000

Save text as JSON as comments but the file itself is a PNG so that you can use it as an image (like previewing it) as they would ignore the comments. However, the OP’s editor can load the file back, parse the comments, and get the original data and continue to edit. Just one file to maintain. Quite clever actually.

The State of Web Dev AI 2025

chown — Thu, 17 Apr 2025 11:40:59 +0000

Article URL: https://2025.stateofai.dev/en-US

Comments URL: https://news.ycombinator.com/item?id=43715352

Points: 1

# Comments: 1

New comment by chown in "Llama.cpp supports Vulkan. why doesn't Ollama?"

chown — Fri, 31 Jan 2025 13:58:12 +0000

I totally agree with this. I wanted to make it really easy for non-technical users with an app that hid all the complexities. I basically just wanted to embed the engine without making users open their terminal, let alone make them configure. I started with llama.cpp amd almost gave up on the idea before I stumbled upon Ollama, which made the app happen[1]

There are many flaws in Ollama but it makes many things much easier esp. if you don’t want to bother building and configuring. They do take a long time to merge any PRs though. One of my PRs has been waiting for 8 months and there was this another PR about KV cache quantization that took them 6 months to merge.

[1]: https://msty.app

New comment by chown in "I Run LLMs Locally"

chown — Mon, 30 Dec 2024 00:47:17 +0000

I wanted to present it as - “Msty As x Alternative”. But I think maybe I like Compare better. I will think about changing it. Thank you for the suggestion.

New comment by chown in "How I run LLMs locally"

chown — Sun, 29 Dec 2024 22:17:05 +0000

If anyone is looking for a one click solution without having to have a Docker running, try Msty - something that I have been working on for almost a year. Has RAG and Web Search built in among others and can connect to your Obsidian vaults as well.

https://msty.app

New comment by chown in "Using an 8K TV as a Monitor"

chown — Tue, 29 Oct 2024 17:20:19 +0000

I am looking for a 55” 4K OLED. Do you have a recommendation? And are there any technical caveats with it? (I use a Mac primarily). Thank you

New comment by chown in "Ask HN: What are you working on (September 2024)?"

chown — Mon, 30 Sep 2024 04:02:04 +0000

I am working on making using LLMs easy for everyone. Focus is to make users productive rather than having them configuring their environment to death. Wrote this app for my wife who, even as a smart software engineer, was getting overwhelmed with AI and LLMs.

https://Msty.app

New comment by chown in "Zen, a Arc-like open-source browser based on the Firefox engine"

chown — Wed, 21 Aug 2024 14:16:17 +0000

I've recently started using Arc mostly out of FOMO and there are parts that I like and parts I don't. I have been a Firefox user for a long time before that so glad to see something similar that's one of the major priorities is the aesthetics and I very much appreciate that.

I tried to use it on my macOS Apple Silicone and got an error about it being broken and macOS suggested to trash it. Not sure if it is a bug issue. Will come back and try it again though to give it a second chance :)

New comment by chown in "Llama 3.1"

chown — Tue, 23 Jul 2024 16:10:03 +0000

Wow! The benchmarks are truly impressive, showing significant improvements across almost all categories. It's fascinating to see how rapidly this field is evolving. If someone had told me last year that Meta would be leading the charge in open-source models, I probably wouldn't have believed them. Yet here we are, witnessing Meta's substantial contributions to AI research and democratization.

On a related note, for those interested in experimenting with large language models locally, I've been working on an app called Msty [1]. It allows you to run models like this with just one click and features a clean, functional interface. Just added support for both 8B and 70B. Still in development, but I'd appreciate any feedback.

[1]: https://msty.app

New comment by chown in "Gemma 2: Improving Open Language Models at a Practical Size [pdf]"

chown — Thu, 27 Jun 2024 15:30:01 +0000

If you are still looking for it, I just made it available on an app[1] that I am working on with Gemma2 support.

https://msty.app

New comment by chown in "Gemma 2: Improving Open Language Models at a Practical Size [pdf]"

chown — Thu, 27 Jun 2024 15:28:14 +0000

This is a great release! If you are looking to try it locally with a great interface, I am working on an app [1] and I just pushed an update to support Gemma2.

1: https://msty.app

Claude 3.5 Sonnet vs. GPT-4o

chown — Fri, 21 Jun 2024 11:58:44 +0000

Article URL: https://msty.app/blog/claude-3.5-sonnet-vs-gpt-4o

Comments URL: https://news.ycombinator.com/item?id=40748651

Points: 4

# Comments: 0

New comment by chown in "Show HN: ChatGPT UI for rabbit holes"

chown — Fri, 31 May 2024 13:54:45 +0000

I am working on something similar [1] that you might like. It doesn't have the canvas view but that along with a git graph like UI is something that I haven't thinking of adding.

1: https://Msty.app

New comment by chown in "Show HN: ChatGPT UI for rabbit holes"

chown — Fri, 31 May 2024 13:50:01 +0000

I am working on an app [1] that does very similar as far as the branching goes (minus the right hand side visual which I have plans to support something very similar but along with a git like graph).

1: https://msty.app

Llama 3 vs. GPT-4 vs. Gemini Pro

chown — Fri, 19 Apr 2024 11:26:41 +0000

Article URL: https://msty.app/blog/llama3-vs-gpt-4-vs-gemini-pro

Comments URL: https://news.ycombinator.com/item?id=40085447

Points: 2

# Comments: 0

New comment by chown in "Meta Llama 3"

chown — Thu, 18 Apr 2024 22:34:28 +0000

Yes, if CUDA drivers are installed it should pick it up.

New comment by chown in "Meta Llama 3"

chown — Thu, 18 Apr 2024 17:21:27 +0000

If anyone is looking to try 7B locally really quick, we have just added it to Msty.

[1]: https://msty.app

New comment by chown in "Mixtral 8x22B"

chown — Wed, 17 Apr 2024 17:27:37 +0000

You can try Msty as well. I am the author.

https://msty.app