Hacker News: maalber

New comment by maalber in "Show HN: I have created an alternative for Miro"

maalber — Tue, 18 Nov 2025 15:16:27 +0000

Curious about your main motivation to build this. What sets this apart from Miro you think?

New comment by maalber in "Show HN: You know browser-use, here's human-use for LLMs to get info from humans"

maalber — Thu, 15 May 2025 16:24:36 +0000

Haha, interesting! What made you stop?

I might get back to you regarding the domain

New comment by maalber in "Show HN: You know browser-use, here's human-use for LLMs to get info from humans"

maalber — Wed, 14 May 2025 12:47:02 +0000

Fair point, I gathered the crowdsourcing element to be implicit but I included it for completeness. The novelty here is the direct interface to LLMs.

Show HN: You know browser-use, here's human-use for LLMs to get info from humans

maalber — Wed, 14 May 2025 12:17:44 +0000

We made human-use. Similar to how browser-use connects agents to the web, human-use connects agents to people all over the world in real-time using the Rapidata API. This allows the LLM to crowdsource human feedback and insights when it deems necessary.

Free to use for anyone, you can enable your agent to use humans in real-time to:

- Do preference research - Check for hallucinations - Capture sentiment - Get feedback - etc. Whatever you would want from humans.

We expose certain parts of the Rapidata API to the agent through the MCP server framework. Additionally we provide a custom client. More details are available on the repo.

Happy for feedback and to answer any questions.

Comments URL: https://news.ycombinator.com/item?id=43983619

Points: 7

# Comments: 4

New comment by maalber in "First large scale evaluation of 4o Image Generation from OpenAI"

maalber — Thu, 27 Mar 2025 13:42:55 +0000

I thought OpenAI had been sleeping a bit and given up on the image generation race. However, with the recent release of the oddly named 4o Image Generation model (Why not continue with the DALL-E naming scheme? I personally love the pun) it looks like they cooked up one hell of a model.

If you are into visual GenAI you have probably already seen many examples of quite incredible outputs from the new model. However, we decided that we wanted to make a large scale evaluation, based on 200k human responses across 13k image pairings.

Unfortunately that also meant that we had to generate a large amount of new images, and since OpenAI have not yet opened up API access, we had to do it manually through the UI :(.

The benchmark tests the model in coherence, prompt-alignment, and overall aesthetic preference. Especially for the first two, OpenAI's new model is very far ahead of the competition.

Check out the detailed results and the collected data which is openly available on huggingface!

Let me know if you have questions or feedback!

Show HN: First large scale evaluation of 4o Image Generation from OpenAI

maalber — Thu, 27 Mar 2025 13:42:55 +0000

Article URL: https://huggingface.co/datasets/Rapidata/OpenAI-4o_t2i_human_preference

Comments URL: https://news.ycombinator.com/item?id=43493576

Points: 3

# Comments: 1

New comment by maalber in "Show HN: 150+ products launched in 7 days on this fair Product Hunt alternative"

maalber — Fri, 31 Jan 2025 12:25:51 +0000

Can definitely relate to the feeling of getting buried on producthunt! Nice work on this, might just have to try it out.

New comment by maalber in "Show HN: HDR Steganography – one file / two images"

maalber — Fri, 31 Jan 2025 12:18:42 +0000

Cool! Did not know about this. I was not able to see anything other than the pipe - which I assume is the SDR versions, maybe some clearer instructions/limitations (and description of what you should expect to see) would be beneficial.

New comment by maalber in "Show HN: Slipbox – On-Device Transcription for Meetings, Podcasts and Videos"

maalber — Thu, 30 Jan 2025 13:10:47 +0000

Can you provide some context or additional info?

New comment by maalber in "Show HN: I made a job board exclusively for tech internships and new grad jobs"

maalber — Thu, 30 Jan 2025 13:09:29 +0000

Looks nice. What do you do to fetch the job postings?

Looks like currently you only support jobs in the US, is that correct?

New comment by maalber in "Show HN: I Created a Pomodoro Timer"

maalber — Tue, 28 Jan 2025 14:35:54 +0000

Why does it show Chinese characters in the tab title once the countdown starts? Is this intended? 番茄工作法

New comment by maalber in "Show HN: Earthguessr, GeoGuessr, but with Satellite Imagery"

maalber — Tue, 28 Jan 2025 11:23:41 +0000

Pretty cool! And also really difficult as it turns out. Love that you can try it without signing up! Runs quite smooth and I like the simplicity of the UI. Maybe a button to return to the starting position is missing?

New comment by maalber in "Show HN: I made a speech generator for all occasions"

maalber — Mon, 27 Jan 2025 14:35:33 +0000

Call me old fashioned, but I think a speech should be something personal that reflects you and the person/people on the receiving end of the speech. If you do not know what to say, then maybe there is no need for a speech. That being said, it could be helpful to some people that have something particular things on their mind, but unsure how to structure it into a speech.

Nice job on finishing this project though!

New comment by maalber in "Show HN: Puzzle Startup Website (WIP)"

maalber — Mon, 27 Jan 2025 14:27:42 +0000

Looks cool!

Did not really manage to get very far yet, but maybe I will revisit later. I was very confused by frequently going to that landing page, which is still WIP, but I guess it will make more sense to me if I spend some more time. In general I was missing a bit of intro, but I assume that is part of the experience

New comment by maalber in "Show HN: Prostir – A Minimalist App for Planning"

maalber — Mon, 27 Jan 2025 10:26:10 +0000

Checked it out quickly, looks cute and inviting.

Is there a reason you did not submit the thread with the link? I was a little bit confused that the title did not take me to the link and I think most HN users would expect that as well - just a pointer :)

New comment by maalber in "Show HN: Prism – An AI-Driven Generative Art System That Evolves over Time"

maalber — Fri, 24 Jan 2025 14:05:31 +0000

Sounds really cool, but i agree with the previous comment that some example would be a very cool, as cloning and running the repo is a bit cumbersome to quickly check it out.

New comment by maalber in "Show HN: Factory Icon – SVG Icon Generator"

maalber — Thu, 23 Jan 2025 13:24:23 +0000

Can you elaborate a bit on the technical details?

What sets this apart from a lot of the similar tools out there?

Do you train your own AI or use off-the-shelf stuff? Do you use an image generator that you convert to SVG or do you output SVGs directly?

New comment by maalber in "Show HN: Draw 1-bit pixel art every day"

maalber — Thu, 23 Jan 2025 13:21:43 +0000

Cool idea, simple interface.

What are your hopes with this? Is it just for yourself to use, or do you hope to get a large gallery of submissions? I was hoping I could submit to the gallery without logging in, but in retrospect I do see why that probably should not be allowed

New comment by maalber in "Show HN: Photo to Video AI – Experimenting with motion diffusion models"

maalber — Thu, 23 Jan 2025 13:17:10 +0000

Can you elaborate on the technical details? Have you trained your own model? Or using something off the shelf?

What was your motivation for creating this?

New comment by maalber in "Show HN: I made AI Infographic Generator Tool that can make infographics easily"

maalber — Thu, 23 Jan 2025 08:12:27 +0000

I agree that in my experience, AI image generation does generally still struggle a lot with generating nice simplistic graphics relevant for these types of uses. However, I think the idea of having a large enough catalogue of graphics, pictograms, and backgrounds that an "AI" could choose from based on the instructions would give a much more customized experience.