Hacker News Reader

GaggiXon Claude Sonnet 4.6

It would be cool, right now the mini and nano models are stuck at GPT-5

GaggiXon Chess engines do weird stuff

I read "girl.surgery" and guessed.

GaggiXon Chess engines do weird stuff

https://cosmo.tardis.ac/files/2026-02-12-az-rl-and-spsa.html

Response from the author of Viridithas, there is a link to this engine in her webpage.

GaggiXon The long tail of LLM-assisted decompilation

Curating a benchmark for reverse engineering functions doesn't seem a bad idea actually

GaggiXon Dark web agent spotted bedroom wall clue to rescue girl from abuse

There is only one location shown in the images, in the past there were several and much clearer, I cannot image how difficult it must be to find it if the europol cannot find it in 2026.

Old thread for context: https://news.ycombinator.com/item?id=19469681

GaggiXon Show HN: Microgpt is a GPT you can visualize in the browser

Wtok and Wpos should be 26-dim along one of the axis but it shows a 16x16 matrix be default, fc1 instead 16x64 with the default settings (not 16x16).

GaggiXon An AI agent published a hit piece on me – more things have happened

I had fun with AI detectors in particular for images, even the best one (Hive in my opinion) was failing miserably with my tests, maybe the one trained on text are better but I find it hard to trust them, in particular if someone know how to fiddle with them.

GaggiXon An AI agent published a hit piece on me – more things have happened

>These tools are not perfect, but they're right more often than they're wrong.

Based on what in particular? The only time I have used them is to have a laugh.

GaggiXon Qwen-Image-2.0: Professional infographics, exquisite photorealism

I have generated my own using your prompt and post it in the previous comment. You haven't posted a z-image one of Atlantis. I'm not at home to try but I have trained lora for z-image (it's a relatively lightweight model), I know the model, it's not as good as nano banana pro. Use what you prefer.

GaggiXon Qwen-Image-2.0: Professional infographics, exquisite photorealism

>Because it's too easy obviously.

Still the vast majority of models fail at delivery an image that looks real, I want realism for a realistic settings, if it can't do that than what's the point. Of course you can always pay people and equipment to make the perfect photo for you ahah

If the image of z-image turbo looks as good as the nano banana pro one for you, you are probably too used to slop that a model that do not produce obvious artifacts like super shiny skin it's immediately undistinguishable from a real image (like the nano banana pro one that to me looks as real as a real photo) and yes I'm ignoring the fact that in the z-image-turbo the cup is too large and the bag is inside the chair. Z-image is good (in particular given its size) but not as good.

GaggiXon Qwen-Image-2.0: Professional infographics, exquisite photorealism

>In your example, z-image and Nano Banana Pro look basically equally photorealistic to me

I disagree, nano banana pro result is on a completely different league compare to flux.2 and z-image.

>But anyway, realistic environments like a street cafe are not suited to test for photorealism

Why? It's the perfect settings in my opinion.

Btw I don't think you are using nano banana pro, probably standard nano banana, I'm getting this from your prompt: https://i.ibb.co/wZHx0jS9/unnamed-1.jpg

>Nano Banana Pro is a Gemini scaffold which uses Imagen to generate an initial image, then Gemini 3 Pro writes prompts to edit the image for much better prompt alignment.

First of all how should you know the architecture details of gemini-3-pro-image, second of all how the model can modify the image if gemini itself is just rewriting the prompt (like old chatgpt+dalle), imagen 4 is just a text-to-image model, not an editing one, it doesn't make sense, nano banana pro can edit images (like the ones you can provide).

GaggiXon Qwen-Image-2.0: Professional infographics, exquisite photorealism

Are you sure you are not confusing nano banana pro for nano banana, z-image still has a bit of AI look that I do not find with nano banana pro, example for a comparison: https://i.ibb.co/YFtxs4hv/594068364-25101056889517041-340369...

Also Imagen 4 and Nano Banana Pro are very different models.

GaggiXon Qwen-Image-2.0: Professional infographics, exquisite photorealism

For me the only model that can really generate realistic images is nano banana pro (also known as gemini-3-pro-image). Other models are closing the gap, this one is pretty meh in my opinion in realistic images.

GaggiXon We tasked Opus 4.6 using agent teams to build a C Compiler

Clang is not written in Rust tho

GaggiXon Voxtral Transcribe 2

>So it's not just whisper v3 under the hood?

Why it should be Whisper v3? They even released an open model: https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-26...

GaggiXon Voxtral Transcribe 2

Gpt4o mini transcribe is better than whisper, the context is the parent comment.

GaggiXon Voxtral Transcribe 2

Gpt4o mini transcribe is better and actually realtime. Whisper is trained to encode the entire audio (or at least 30s chunks) and then decode it.

GaggiXon A sane but bull case on Clawdbot / OpenClaw

>Having something that can actually parse "yep lets do 4pm tomorrow" from texts and create calendar holds is the kind of thing that's always felt 5 years away.

Isn't that just Google Assistant? Now with Gemini it seems to work like a LLM with tools.

GaggiXon Anki ownership transferred to AnkiHub

Even in the worst-case scenario, Anki is already perfect for me as is.

GaggiXon Antirender: remove the glossy shine on architectural renderings

This is just a Nano Banana wrapper I imagine.

GaggiXon Emoji Design Convergence Review: 2018-2026

Well the Taiwan flag doesn't appear on mainland china phones, I think the phone does fall back to the TW letters.

GaggiXon Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT

If people want an AI as a boyfriend at least they should use one that is open source.

If you disagree on something you can also train a lora.

GaggiXon Show HN: One Human + One Agent = One Browser From Scratch in 20K LOC

Maybe you can divide the task into verifiable environments like an HTML5 parser environment where an agent is going to build the parser and also check the progress against a test suites (the https://github.com/html5lib/html5lib-tests in this case) and then write the API into a .md, the job of the human is going to be at the beginning to create the various environments where the agents are going to build the components from (and also how much it can be divided into standalone components).

GaggiXon Show HN: One Human + One Agent = One Browser From Scratch in 20K LOC

It would be really cool if it was able to render Wikipedia correctly, I really like the idea of a browser with minimal dependencies having the ability to navigate most static websites, this one for now compiles instantly and it's incredibly small.

GaggiXon Iran Protest Death Toll Could Top 30k, According to Local Health Officials

I don't like promoting gore websites but in watchpeopledie and search Iran you can count yourself at least hundreds of body from all the videos, often in a single location, usually the aftermath.

GaggiXon From stealth blackout to whitelisting: Inside the Iranian shutdown

A friend of mine (from Iran) managed to send me a few messages on January 18th via Telegram (Telegram is very popular in Iran) when the situation was though to be resolving and then nothing, blackout again.

And even when the blackout was not present, my friend had to used some complex V2Ray server (in Iran) to another server (in Germany) to connect and it was shared by other people, so if he cannot connect probably 99% of other people in his area cannot also connect outside.

GaggiXon The coming industrialisation of exploit generation with LLMs

The vulnerability was found by Claude:

>This is true by definition as the QuickJS vulnerability was previously unknown until I found it (or, more correctly: my Opus 4.5 vulnerability discovery agent found it).

GaggiXon The coming industrialisation of exploit generation with LLMs

The vulnerability was found by Opus:

"This is true by definition as the QuickJS vulnerability was previously unknown until I found it (or, more correctly: my Opus 4.5 vulnerability discovery agent found it)."

GaggiXon The coming industrialisation of exploit generation with LLMs

After setting the environment and the verifier you can spawn as many agents as you want until the conditions are met, this is only possible because they run without human assistance, that's the "industrialisation".

GaggiXon The coming industrialisation of exploit generation with LLMs

The NSO Group going to spawn 10k Claude Code instances now.