Hacker Newsnew | past | comments | ask | show | jobs | submit | husky8's commentslogin

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

One would imagine given the name that it would specialize in codecs

Codex is actually short for `Code Execution`

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

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


Getting this message - "Oops! This audio could not be loaded."


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.


Seems shortsighted to offer something like this with zero information about how it works. If your target market is privacy-conscious, slapping a "Privacy by Design" badge and some vague promises is probably not very convincing. (Also, the homepage claims "Your conversations remain on your device and are never sent to external servers," yet the ProductHunt page says "All requests are handled locally on my own farm and all data is burned" -- which is it?)


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.


magic word is hackernews. expires in 24hr (5/4 11:25p ET)

use responsibly


This can also serve as a useful reference for your AI Agent.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: