Binx @BinxNet

Backend SWE | Tinkerer | Data Surfer dreaming of electric sheep Joined April 2022

Tweets

3K
Followers

3K
Following

1K
Likes

15K

scaredofboobs🪲 @boobs_scary

2 months ago

I hacked the engine out of comfyUI's image-to-3d to utilize llama.cpp and now it can run quantized models and this workflow is down to 4g of VRAM. You're paying $400 a month in meshy credits for something you can run on a GPU from 2018.

scaredofboobs🪲 @boobs_scary

2 months ago

I locked myself in a room for 48 hours and didn't let myself leave until I had 3D meshes that rivaled meshy running on 12gb of VRAM. LET HIM COOK.😤

29 25 499 109K 313

52 130 2K 81K 1K

View Details

Binx @BinxNet

2 months ago

@sudoingX There are plenty of low-hanging fruit when it comes to improvements to optimizations, also... which Google's dropped on everyone. Fine-tuning dense models to compress knowledge to fit on edge devices is coming, also. The future for consumer hardware is looking bright.

0 0 0 14 0

View Details

@

4 months ago

I'm actually going feral. Look at this shit.

Teddy Sjöström @TheoVanGrind

9 years ago

@Jonathan_Blow regarding software bloat outpacing hardware progress: found my 18y old Pentium II 400mhz laptop and fired up MS Word 98...

155 1K 10K 0 1K

27 2K 35K 1.1M 3K

View Details

monerobull @monerobull

4 months ago

Mega-corps buying black market data from shadow libraries, using untraceable crypto currency, to build a digital god. Cyberpunk 2026

Ed Newton-Rex @ednewtonrex

4 months ago

A few months ago I was curious to know how much Anna's Archive was charging AI developers for access to their massive library of pirated works for training - so I emailed them saying I was interested in buying access. Here is their reply. They are charging $200,000 (payable via

182 610 4K 1.0M 2K

27 578 4K 208K 959

View Details

Benji Taylor @benjitaylor

4 months ago

Introducing Agentation: a visual feedback tool for agents. Available now: ~npm i agentation Click elements, add notes, copy markdown. Your agent gets element paths, selectors, positions, and everything else it needs to find and fix things. Link to full docs below ↓

243 435 5K 720K 6K

View Details

GitHub Projects Community @GithubProjects

4 months ago

Tiny alternative discord client with a smaller footprint, snappier startup, themes, plugins and more

18 81 2K 87K 1K

View Details

cocktail peanut @cocktailpeanut

4 months ago

Great tips here, the best part is you can also do all this with nothing but your PC locally. LTX-2 available open source, and there are tons of good enough open source image generation models that are fast enough.

TechHalla @techhalla

4 months ago

This is some of the craziest stuff you can make with AI right now. All powered by the new LTX Audio to Video. Everything you need to know is down below 👇

25 14 168 18K 117

1 2 27 3K 12

View Details

Anthropic @AnthropicAI

4 months ago

We’re publishing a new constitution for Claude. The constitution is a detailed description of our vision for Claude’s behavior and values. It’s written primarily for Claude, and used directly in our training process. anthropic.com/news/claude-ne…

518 968 8K 3.4M 5K

View Details

𝖓𝖎𝖓𝖊 🕯 @atlanticesque

5 months ago

I actually do think AI is in a bubble But some people seem to think the AI bubble popping would mean, like, that LLMs get un-invented

338 680 21K 572K 723

View Details

Binx @BinxNet

4 months ago

6 years into SWE dying in 6 months btw

Wes Roth @WesRoth

5 months ago

"Software Engineering Will Be Automatable in 12 Months," Anthropic CEO Dario Amodei predicts that AI models will be able to do 'most, maybe all' of what software engineers do end-to-end within 6 to 12 months, shifting engineers to editors.

1K 2K 12K 4.5M 5K

0 1 1 85 0

View Details

Binx @BinxNet

4 months ago

@0xSero @fatihozgen85 nah you can just give it the contents of a buffer and any delimiters you wanna specify as part of a harness, then let it fill in with a hotkey/motion

1 0 4 273 2

View Details

Binx @BinxNet

4 months ago

@0xSero @fatihozgen85 you can… make a thing that lets it do that…. so yes?

1 0 1 276 0

View Details

ThePrimeagen @ThePrimeagen

4 months ago

its crazy to think that you are not responsible for the code you produced.... like have you ever worked anywhere? ... wait a second

Тsфdiиg @tsoding

5 months ago

It's funny how radically the behavior of humans changes when you hold them accountable for what the LLMs generate.

103 2K 22K 646K 2K

50 47 2K 133K 158

View Details

Purz.ai @PurzBeats

5 months ago

How to Actually Control Style with LTX-2 LoRAs

5 45 494 25K 428

View Details

Charly Wargnier @DataChaz

4 months ago

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on @huggingface 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This @nvidia model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

157 667 6K 564K 7K

View Details

Md Ismail Šojal 🕷️ @0x0SojalSec

5 months ago

Zero-Click iPhone Hack via WhatsApp Images : Quarkslab blog post analyzing the patch for Apple's iOS CVE-2025-43300 (a zero-click vulnerability in ImageIO via malformed DNG images, potentially exploitable through apps like WhatsApp) Fascinating patch analysis: Incredible how just 2 bytes patched CVE-2025-43300, a zero-click out-of-bounds write in Apple's ImageIO. Triggered by sneaky DNG images, CVE-2025-43300 stemmed from a mismatch in DNG/JPEG parsing, causing double writes and potential code execution. that could hijack your device via rogue images. Apple's August 2025 patch - blog.quarkslab.com/patch-analysis…

11 179 908 133K 571

View Details

Chubby♨️ @kimmonismus

4 months ago

This sounds incredible: FlashLabs just open-sourced Chroma 1.0, an end-to-end real-time speech-to-speech model with high-fidelity voice cloning (~135–150ms TTFT) positioned as an open alternative to OpenAI’s Realtime model, with code/weights, paper, and demos released.

FlashLabs @flashlabsdotai

4 months ago

Today we’re releasing Chroma 1.0 → the world first open-source, end-to-end, real-time speech-to-speech model → with personalized voice cloning Trained by FlashLabs. Deployed on FlashAI👉 flashlabs.ai/flashai-voice-… An open research-grade alternative to the @OpenAI Realtime

145 238 1K 1.2M 1K

18 66 829 73K 652

View Details

Binx @BinxNet

4 months ago

average claude debugging experience

ThePrimeagen @ThePrimeagen

4 months ago

I took Opus 4.5 Max Mode for the ultimate test. I asked it to search my code base for bugs I took a lot of pride in this code, all hand rolled, by the sweat of my brow. It was mine and it was good. Claude found 15 bugs I was devastated So I went to the first bug, and asked

579 299 7K 633K 879

0 0 0 63 0

View Details

Sean Heelan @seanhn

5 months ago

Blog post: On the Coming Industrialisation of Exploit Generation with LLMs sean.heelan.io/2026/01/18/on-… TL;DR: I ran an experiment with GPT-5.2 and Opus 4.5 based agents to generate exploits for a zeroday QuickJS bug. They're pretty good at it. Code: github.com/SeanHeelan/ana…