HNHacker News
TopNewBestAskShowJobs

Miguel07Code

43 karma · joined April 15, 2024

21, computer engineer student that loves to build stuff.

X: https://x.com/miguel07code Email: miguel07alm@protonmail.com GitHub: https://github.com/Miguel07Alm

submissionscomments
Miguel07Code··on Show HN: HyperFrames – OSS Agentic HTML Video Framework for Agents
Yep, the blog is more technical, so non-tech users would just install the skill with claude code, openclaw, hermes agent or whatever harness and do a video. Related to what you did, you can also use Canvas inside HyperFrames, etc, so if you need something feel free to open a pr and I'll review it if you tag me
Miguel07Code··on Show HN: ArXivTok
Exactly, I think that in this case using ML models that are experts in papers can be more useful and that type of models can run locally so it's the best option.
Miguel07Code··on Show HN: ArXivTok
Thanks! I don't track anything; it just shows sorted papers from the current date.

Maybe I'll implement a basic recommendation algorithm locally, because right now, an LLM implementation wouldn't be sustainable.

Miguel07Code··on Show HN: ArXivTok
I'm rolling a new version up now, it'll be live in 2 minutes.
Miguel07Code··on Show HN: ArXivTok
I'll try to improve that in a moment.
Miguel07Code··on Show HN: ArXivTok
Added! Try it out.
Miguel07Code··on Show HN: ArXivTok
Yeah, I'll add it quickly.
Miguel07Code··on Show HN: ArXivTok
I'll add it as a source too.
Miguel07Code··on Show HN: ArXivTok
Just by imagining it, it would be a lot of fun haha.
Miguel07Code··on Show HN: ArXivTok
Thanks! I'll text you here when I add the feature. It wouldn't be core, so I think that having two modes where you can read easily papers with LLms or not will be of great help.
Miguel07Code··on Show HN: ArXivTok
Thanks for the feedback, I think that it would be like having 2 modes with a toggle: unhingered summaries from local LLMs or the real summaries.
Miguel07Code··on Show HN: ArXivTok
That has potential..
Miguel07Code··on Show HN: ArXivTok
Wow, I didn't know that.. It's really ironic
Miguel07Code··on Show HN: ArXivTok
Mm maybe running a local LLM for doing it would be a great idea, I'll try to do that and if it doesn't work well, I'll consider doing it with an API.
Miguel07Code··on Show HN: ArXivTok
Added!
Miguel07Code··on Show HN: ArXivTok
That would be cool, I'll consider it!
Miguel07Code··on Show HN: ArXivTok
Noted, I'll add it now
Miguel07Code··on Show HN: ArXivTok
Hahaha surely one is building it right now
Miguel07Code··on ArXivTok
Yeah, I used Copilot instead of Cursor.
Miguel07Code··on Show HN: ArXivTok
I think I have that now covered, you can try it out and tell me if it works if you want.
Miguel07Code··on Show HN: ArXivTok
I added now the MedRxiv API, you can try it out and tell me if you notice something weird.
Miguel07Code··on Show HN: ArXivTok
I saw that medrxiv has an API so I'll add it too!

About the behaviour of the scroll it's a bit buggy haha but I'll try to fix that, thanks for the feedback.

Miguel07Code··on ArXivTok
That would be nice, I'll add it to the roadmap.
Miguel07Code··on ArXivTok
Thanks for the feedback! I'll add Show HN then.
Miguel07Code··on ArXivTok
Yeah, I filtered it mandatorily about AI or computer science
Miguel07Code··on Reduce Video Editing Time with AI-Powered Natural Language Commands
I’ve been working on something that might just save you a ton of time if you edit videos.

As someone who codes and creates content about programming, I got tired of wasting hours on repetitive editing tasks. So, I built my own video editor that automates all of that with AI.

It’s simple: you give it commands like “Put the subtitles just below my chin and make them bold” and it does exactly that. No need to click around or manually adjust things, just tell the tool what you want and it handles the rest.

This isn’t about replacing creativity, it’s about speeding up the boring stuff so you can focus on the actual content. I’ve got it set up in a way that boosts productivity, so you can get more done in way less time.