For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | ddmma's commentsregister

This reminds me of my first more serious gpt based project, AIRadioHost. Been starting after the ElevenLabs voice cloning performance and had a lot of fun with online/ FM stations interest plus even paying customers. But I wasn’t pursuing to build any business out of this, more to have a way to get the latest AI news and trends while cycling. The platform automation, voices and text processing is fully openai’s support. You can listen at https://airadiohost.com


Qriton solved the "inference problem" mainly you can do operations on a synthetic brain, similar to a database, called surgery


Three parallel terminals of coding agents and crosswords magazine until they complete their jobs. Work with real experts and solve real world problems.


I’m on my 40s and building a platform to support my late cognitive decline. Tools that shaped human existence.


Would love to hear more, if you are happy sharing!


I would also like to hear more!


I'd like to hear more


The first tool that lets you directly program a neural network's behaviour — not train, not fine-tune, not prompt-engineer. Program. https://pypi.org/project/qriton-hlm/


Ideally your mind will be uploaded to META cloud and then live in that simulation as long there is electricity on this planet. With the Oculus you can talk to your ancestors and connect to other dimensions. As long your social graph peers don’t post so much there a lot of push from the dystopian algorithms.


Managed to build a full autonomous ai radio from ground up. Let me know if need support on this. I’m also hosting community radio back in my hometown.


Welcome to the agentic future, might need some baricade with human only, DNA captcha


might makes right they say, but if feels weak here, it's going to be required, hopefully sooner than later


Good hygiene. But the gap they admitted—NL attacks, prompt injection—won't get fixed by pointing another LLM at it.

LLM auditing LLM is like RAG solving reasoning. Same blindspot, twice.


They will pay upfront or put some geopolitical pressure https://www.bbc.com/news/articles/c24g8v6qr1mo


is back online


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

Search:

HN For You