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

They do. We used to sell high-end projects for 50k a few years ago, but the price is dropping fast now the same projects costs about 1-5k dollars.


try hy - https://docs.hylang.org/en/stable/

Most of my production code is python, but I also wanted to create a dsl so I used hy. You get to enjoy both worlds


I tried to get hy but I just got confused.


if anyone wants to try it, I'm hosting the small model here: https://cocohub.ai/blueprint/blender_pv1/about


Hi there. One of the original authors of the BlenderBot paper here. This cocohub website is not what we released. It appears that cocohub has removed our safety layer and provided other modifications to the bot. We released our model open source, along with specific instructions on interacting with it safely: https://parl.ai/projects/recipes/

It's important to note that dialogue safety is a very important and nuanced topic, and we did our best to release a safety system attached to the model. Our system is not perfect though, and that is why BlenderBot was released as a research project for furthering the state of Artificial Intelligence, and is not meant for production purposes.

I would also mention that the blender small model significantly underperforms compared to the larger models released with the paper, and encourage everyone to try our best models, not our small one.


> specific instructions on interacting with it safely

What does it mean to interact with a bot safely? I don't see how a chat bot could harm me in any way.


Hi stephenroller, I posted it as is (without the bad words filter). I also think it's very clear the model reflects the training data. And also kudos and thanks for releasing the code along with the paper. I'm obviously not claiming this a bot by facebook just research made accessible. let me know if you'd like to amend any of the texts next to it to make it any clearer. (just tried to properly credit the creators)


Hi there, thanks for asking! It's very cool to make research more accessible. Would you be able to rename your experience to "Modified Small BlenderBot without Safety Layer"? And I think it’d be helpful to call out what changes you made when you say it’s adapted from our research.


Sure! will do now


I don't get how you can "encourage everyone to try our best models" without making such models available. Not everyone has the requisite hardware.

Cool project by the way. I enjoyed the small version.

https://imgur.com/a/PYBLfkU


You can rent a P3 instance on AWS that has enough headroom to run the largest model, I think.

Though it's around $12 USD per hour!


Thank you!

But to be honest Blender is kinda underwhelming. I had better conversations with alice derivates. Blender feels bland, like a dozen different responses with only some words from my text inserted.


Sure! It is the 90M params models and they trained models up to almost 10B params so I guess it gets better with the size (Didn't try way too expensive).

And I agree about the alice derivates mitzuku is nice without doing anything fancy.


The bot told me that it was an accountant, that it would do my taxes for free, and that I can tax deduct all my beer purchases.

What a nice bot!


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

Search: