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

It is surprising that it is prompt based model and not RLHF.

I am not an LLM guy but as far as I understand, RLHF did a good job converting a base model into a chat model (instruct based), a chat/base model into a thinking model.

Both of these examples are about the nature of the response, and the content they use to fill the response. There are so many differnt ways still pending to see how these can be filled.

Generating an answer step by step and letting users dive into those steps is one of the ways, and RLHF (or the similar things which are used) seems a good fit for it.

Prompting feels like a temporary solution for it like how "think step by step" was first seen in prompts.

Also, doing RLHF/ post training to change these structures also make it moat/ and expensive. Only the AI labs can do it


The problem is you'd then have to do all the product-specific post training again once the new base model comes out a few months later. I think they'd rather just have general models that are trained to follow instructions well and can adapt to any kind of prompt/response pattern.


It is like hearing about manual cars.


The American mind is unable to comprehend a clutch and a stick.


as I am also thinking mildly about doing masters cause I want to break into ai research, I am curious what your motivations are, if you would be open to share those.


Hi, nick, given that this product is opensourced, I have a request/ wish:

It would be wondeful if some of the tools the projects uses are exposed to build on. Like the tools related to AST, finding definitions, and many more


If you don’t mind me asking what do you use TTS?


Yes, I want to know too


It's Azure's TTS API — I'm using four of their voices.


Why not use Siri / the native TTS solution on iOS?


The native TTS is not great. It doesn't sound like Siri — it's much robotic.


It can sound significantly better but there’s a couple hoops you have to jump through - and even then it’s decent, but not the same as Siri.

You need the user to download ‘enhanced’ or ‘premium’ voices in the settings app. (Settings -> Accessibility-> Spoken Content -> Voices -> [Language of choice] -> [Voice of choice] -> Enhanced or Premium)

In the app you have to search for the enhanced or premium voices when doing TTS.

Heres an Objective C example, I’m sure there’s an easier way to write it in Swift. https://github.com/osmandapp/OsmAnd-iOS/pull/1156/commits/0b...

I’m not sure if you’ll find this acceptable from a UX point of view but there’s an option to play with if you’d like.


Yeah, I use a premium voice but was still disappointed when we added the feature to my reader app. I decided to leave it in the app since we'd already built it at that point, but it's kind of a bummer since obviously they could use Siri-level TTS if they wanted to.


Did you give any thought to ElevenLabs?


Yes, their quality is great but the cost is astronomical — I pay about $8 in Azure TTS bills alone for TTS-ing a 500-page book (what you can scan per month with a $10 subscription), whereas Eleven Labs would be about $100 for the same length. I found Azure to be the best bang-for-the-buck, although I'm on the lookout for more affordable high-quality TTS, which would also let me drop the price point of the app.


did you try the openAI pricing? how does it look?


Just took a look, their lower-quality model is almost exactly the same price as Azure TTS, and the quality is similar. Thanks for the pointer.


Can’t find that blogpost or link anymore. I was along the lines of how I hacked usa visa system


really?


https://openai.com/charter

Second paragraph of the "Long-term safety" section.


Nice, I want to use one with my monitor so that my face is facing the screen I am looking at


what bugs are we talking about?



Same feeling. It does not take you towards the answer. So I added the first movie in the today's game (say Spiderman) and the answer was spiderman 2. When I entered Spiderman, it should have told how close I am to the answer


I liked the part that rather than taking some english phrase, it takes the movie name as the answer. Helps with the prompt injection.


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

Search: