Hacker Newsnew | past | comments | ask | show | jobs | submit | more savy91's commentslogin

I still have my NZ90. The hardware was amazing, the software not so much


Is it just a mock up and a landing page or is the MVP actually functional?


The MVP is functional. However, only with test card data.


Am I wrong thinking this could very well be the backbone of an alternative to the Rabbit AI? Where you basically end up having possibly infinite tools for your LLM assistant to use to reach a goal without having to build api integrations.


Yup, it could! There are a lot of players in the generalist personal web agent space but I personally think that use-case will be eaten by big players since fundamental foundation model improvements are required. That being said, Tarsier is a great place to start for building an open-source web agent for automating cool little tasks.

At Reworkd, we're focused on web agents for data extraction at scale, which isn't as hyped as the generalist agents but we find provides a lot of value and already works pretty well.


Function call is there only for api access, unless you create a ChatGPT plugin.

Also, the api allows the developer to force gpt to call a specific function.


> Also, the api allows the developer to force gpt to call a specific function.

Thanks, I might swing around and look at it again. For a side project I went back to normal chat and parsing between ``` and ```


Amazing! I am working on projexts where we use LLMs and Typescript and and besides langchain-js which can be only described as bloatware, I can never find anything and find myself reinvent the wheel most of the time.


Why do you think langchainjs is bloatware?


I worked on something like this for a client and got pretty good results with this model: https://civitai.com/models/6431?modelVersionId=23104

I spent a while looking for decent loras but eventually settled on this because there are just too many porn fine tunes on civitai and it would take a lifetime to test them all.

The product I built allows users to ask pretty much anything (it's a sort of sex chatbot that also sends photos) and the problem is when people start asking super weird stuff and you end up with girls with 4 feet.

Or maybe they like that and it's not a problem at all, who knows.


Thanks for linking your model. This is Nth iteration of my work. I experimented with a chat bot that could send nudes. It's impossible to achieve passable quality if you let user request anything they'd like. Feel free to hit me up on Telegram if you want to chat more about it @samnickelson


Worst part of langchain is the "documentation". Especially the one about the javascript implementation


Python is bad too ……


I was going with "oh yes? Show me what you sell" then I clicked on your username. You are doing an amazing job!


Have you tried this? https://apify.com/vdrmota/contact-info-scraper it can work with 50 input urls at a time.


amazing, thank you


I could say the same for gpt3.5. Through the API I am getting many more "sorry but as a language model" with the prompts I have been using for a while


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

Search: