News for hackers. Stuff that matters.

alishobeiri

Re:How to live forever (using AI) on Sunday November 24, 2024 @11:39AM (#42228763)
Here is my technical write up on how you create your own AI replica by fine-tuning gpt-4o-mini on every text message you have ever sent.

I started working on this because I had lost the love of building. I wanted to just have fun again. Well, this project was fun. Especially the completely unhinged model that I couldn't release publicly.

If you would like to play around my chatbot, try it out at: https://text-ali.com/.

Would love for you to try it out and let me know what you think! I will likely make a Show HN with the website sometime soon as well :)

Re:Show HN: StarHog – See who starred your open source project on Tuesday September 03, 2024 @11:44AM (#41436061)
The way I was approaching it was from the maintainer perspective where I want to engage with the community of stargazers. My experience with that has been fairly good and folks are responsive.

I had a friend who used the original script to reach out to a repo similar to what he was hoping to build and actually got a lot of good feedback as well, so from the small sample size it has generally been positive.

To give a way to protect against potential abuse, I created a form on the homepage where anyone can be asked to be excluded from a StarHog list. Though I am open to hearing suggestions if you might have any as well.

Show HN: StarHog – See who starred your open source project

https://starhog.co/

Over the weekend, I built a small project to help open-source projects better understand who starred their projects.It helps you see the number of stars per day, week, month etc so you can monitor the health and the general trend as well.Lastly, it lets you fetch their public contact info, if you wish to do so.I initally built it as a Python script but after a few friends said they had the same...

( Read More... | 4 comments | 4 points | on HN )
Re:OpenAI blocking API calls from Hong Kong on Sunday July 28, 2024 @02:42AM (#41091629)
Spent some time debugging with a https://vizly.fyi user before realizing that her API calls were being blocked because they were being routed to a server executing in Hong Kong.

Thought it might be valuable to share with the community as well in case anyone has a similar problem.

I just added the ability to run the proxy locally: https://github.com/squaredtechnologies/thread/commit/7575b99...

Will update once I add Ollama support too!

Sorry that is my mistake, to clear it up: 1. Yes the API key here is the OpenAI key 2. The tool at the moment cannot be pointed to local models, though I am adding support for that. My focus right now is the following, in order of priority: - Self-hosting the proxy server (priority) - Adding support for local models

Ideally having the self-hosting would also allow people to switch things to use their own models (hosted) as well if need be.

Hahaha I was not aware of the Slack alternative too hahah point taken
Hahahah point taken, in all fairness, I only knew about Threads (the social media app) when I posted and so I thought it wouldn't overlap. I was worried the word `thread` might overlap in a parallelism sense though wasn't aware of the networking stack. Anyways I appreciate the feedback :)
Hahaha I take the point, I thought I was slick because I got the thread.dev domain and so didn't consider SEO as much. One of the alternate titles we considered was `Show HN: Thread.dev` instead of just `Show HN: Thread` to minimize overlap but last second opted against it. Anyways appreciate the feedback.
Definitely, it is something we are super focused on as it seems to be a use case that is important for folks. Opening up the proxy server and adding local LLM support is my main focus for today and will hopefully update on this comment when it is done :)
It's something we are considering, I think Hex provides a lot of features that aren't available in existing local notebooks (SQL, reactive cell execution) that we hope to integrate for sure. I think both Jupyter and VS Code are really strong players in the space so one of the concerns we have was around whether the feature set would be compelling enough to get people to switch. (Which is why we wanted to post to test the initial reaction :))

The reason we wanted to focus on running things locally is that we were both engineers at big companies in the past, and we didn't have access to tools like Hex but we could use local tools. Our initial thesis is to bring the best development experience local and see if there is an opportunity to build a business model around collaboration features.

I think that's another really good point, it was the first time we have open sourced a project or a library so I wasn't really sure how to best position it with the license. The reason I opted for AGPL was mainly because of the worry that someone bigger could come along and take what we've built and we'd kinda be stuck without an option.

If you'll humour me for a second, just for my own knowledge, I would love to learn a bit more about how you think about the license when deciding whether to use a tool like this or not?

Yeah I think point is very fair, the reason we host it on a proxy server was that we wanted to enable first time users to be able to use it without putting in an API key, the only way we could think of doing that without exposing the key was to host the tool on our own server. We looked to a tool like Cursor that users might be okay with that.

I the think the feedback is very fair that when an API key is present that all the calls should happen locally, and that is something I will take as an action item on us to improve.

Show HN: Thread – AI-powered Jupyter Notebook built using React

https://github.com/squaredtechnologies/thread

Hey HN, we're building Thread (https://thread.dev/) an open-source Jupyter Notebook that has a bunch of AI features built in. The easiest way to think of Thread is if the chat interface of OpenAI code interpreter was fused into a Jupyter Notebook development environment where you could still edit code or re-run cells. To check it out, you can see a video demo here:...

( Read More... | 44 comments | on HN )
Re:The Best Time to Post on HackerNews on Tuesday February 27, 2024 @12:38PM (#39526914)
Oh sorry, I meant as already mentioned by the other commentor. You are right that I forgot to add that to the initial notebook :)

Hahahah I like #3 especially

Re:The Best Time to Post on HackerNews on Monday February 26, 2024 @02:29PM (#39515798)
What I find somewhat funny about this is, I did a whole analysis to find the best time to post on HackerNews, and posted at the best possible time.

But this post, that was posted on what is supposed to be a worse time actually ended up doing better :)

Thanks a lot for checking it out in any case!

Re:The Best Time to Post on HackerNews on Monday February 26, 2024 @02:25PM (#39515752)
Hey java-man,

Thanks so much for checking it out, I am the author of the original notebook. I forgot to mention it initially but the timezone is UTC as was already mentioned.

If you have any feedback, would love to hear it as well!

Re:The Best Time to Post on HackerNews on Monday February 26, 2024 @02:23PM (#39515724)
Hey vivzkestrel,

I am actually the creator of the original notebook. Happy to do more, do you know of any good datasets for these that would be a good starting points?

Re:The Best Time to Post on Hacker News on Sunday February 04, 2024 @01:03PM (#39252651)
Ahh dang, forgot to mention that! The timestamps were Unix time, so the timezone is UTC. Thanks for pointing that out
Re:The Best Time to Post on Hacker News on Sunday February 04, 2024 @11:45AM (#39251800)
Hey HN!

As a weekend project, I analyzed Hacker News posts to figure out what does best. Here are some of the most interesting things I found, let me know if you'd like me to add any others!

The best time to post on HN: - Sundays are the best day to post with posts created between 11am-12pm getting the highest average upvotes

Most popular post of all time: - Stephen Hawking has died (http://www.bbc.com/news/uk-43396008)

There are ~80k posts every 4 months - About 20k posts per month on HN

Best keywords to use in the title: - Any mention of a tech company (google, apple, facebook, etc) or open source seems to do the best

Best performing url to link to: - github.com (not surprising given the strength of open source mentioned above)

Posts with negative titles tend to do better than posts with positive ones - Posts that have negative titles get ~4 more upvotes on average than those that are more positive

The dataset I used for the analysis was: https://huggingface.co/datasets/julien040/hacker-news-posts. Would love to hear what you think and if there's anything else you'd like me to add!

Re:I Made the Ex-Machina Wall (Build Montage) [video] on Thursday October 26, 2023 @05:46PM (#38032110)
This is really cool, congrats!
Re: on Tuesday August 29, 2023 @11:42PM (#37317406)
Yes so it is possible to generate questions automatically, just so I understand the CSV use case better. Is it because you don't trust the application enough to connect a database to the application?
Re: on Tuesday August 29, 2023 @11:41PM (#37317399)
Yes definitely, that is something that I think would be interesting for us to add. Since we are building everything fully on prem, we didn't have a web based product to confuse people, but I think your point stands that have a tangible demo to play with will help users trust the product to eventually run it on prem.

Thanks a lot for the feedback!

Re: on Tuesday August 29, 2023 @11:40PM (#37317392)
This is another way to make sure that the app doesn't overstep it's permissions,

It's still very valid feedback, on our side we should make the permissions of each user very clear and make it clearer that we only do select queries. Will make sure to make those changes! Thanks for the feedback!

Older »