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.
@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.
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 ↓
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.
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.
https://t.co/CJsMIO0uej
"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.
@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
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 🔥
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
- https://t.co/n5xmYSdISi
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.
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 for a unit test. It produced a unit test in mere moments.
I ran the tests and saw it. A broken test. Property test of undefined. Rookie error
Ashamed, but determined I set forth to fix these bugs as penance. So I cracked open nvim getting ready to edit this typescript script
But... The code seemed correct. Weird.
So I checked the test, Claude faked bad data. The setup could never happen
Wtf
It's a lie, the whole thing.
I checked every bug Claude found. Every line item was not a bug. Everyone of them just some condition that cannot exist due to asserts or previous if statements
What an amazing $3s and 20 minutes spent
Normally when I waste time at least I learn something
Blog post: On the Coming Industrialisation of Exploit Generation with LLMs https://t.co/aK4pysY1wD
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: https://t.co/47xHRObhRy