Hacker News: husky8

New comment by husky8 in "Dav2d"

husky8 — Sun, 31 May 2026 13:05:12 +0000

Is codex working on novel decoders 24/7? I hope

New comment by husky8 in "Disagreement Among Frontier LLMs on Real-World Fact-Checks"

husky8 — Thu, 28 May 2026 16:38:32 +0000

Watch the disagreements in real time via refinement pipeline on the results page pingpongit.com

AI was made for junk mail

husky8 — Wed, 13 May 2026 03:45:04 +0000

Article URL: https://junkmailmagic.com

Comments URL: https://news.ycombinator.com/item?id=48117549

Points: 5

# Comments: 0

GlowGoblin – a gift to mb pro users

husky8 — Fri, 01 May 2026 05:38:33 +0000

Article URL: https://github.com/jtc268/glowgoblin

Comments URL: https://news.ycombinator.com/item?id=47971598

Points: 1

# Comments: 0

5 AIs. One Answer on iOS

husky8 — Wed, 25 Mar 2026 21:12:29 +0000

Article URL: https://apps.apple.com/us/app/pingpongit/id6758229301

Comments URL: https://news.ycombinator.com/item?id=47523339

Points: 2

# Comments: 0

CodeCity: Turning a Codebase into a Skyline

husky8 — Sun, 22 Mar 2026 02:06:12 +0000

Article URL: https://verial.xyz/posts/codecity

Comments URL: https://news.ycombinator.com/item?id=47473727

Points: 2

# Comments: 0

New comment by husky8 in "Quantum Computation Lecture Notes (2022)"

husky8 — Fri, 13 Jun 2025 00:32:38 +0000

I made a podcast in NotebookLM once I saw equations. Enjoy https://notebooklm.google.com/notebook/bc7616c4-1c71-4a04-b2...

New comment by husky8 in "OpenAI slams court order to save all ChatGPT logs, including deleted chats"

husky8 — Thu, 05 Jun 2025 03:12:21 +0000

https://speaksy.chat/

Speaksy to the rescue for privacy and curiosity (easy-access jailbroken qwen3 8B in free tier, 32B in paid) May quickly hit capacity since it's all locally run for privacy.

New comment by husky8 in "Chat with an Uncensored LLM"

husky8 — Mon, 05 May 2025 16:15:47 +0000

I thought it'd be interesting to test qwen3 uncensored given the fantastic benchmarks (https://qwenlm.github.io/blog/qwen3/) and realized the barrier to entry for some folks may be high.

I've improved qwen3_8B (named Swift) and qwen3_32B (named Eagle) for hassle-free responses and made access as easy as possible for hacker news folks. The quick responses from Swift are satisfying. These models are run locally on my machine with burned logs. No data is saved or passed on the server side. Hit the nuke button from the menu to 100% clear the client side.

If my GPUs start melting, I'll have to password protect the site. I hope some folks can explore their thoughts freely before then. Open to feedback. The free link is just for yc/hackernews folks https://speaksy.chat/yc

Please use responsibly. There are so many curious thoughts we have that get blocked from exploring via flagship models and I understand why. e.g. in the security space. However, I think curious minds demand an outlet. If you see anything awful, please use the Report Abuse feature by clicking the triple dot on any message.