digitado

About digitado

https://www.digitado.com.br

Posts by :

Multi-Objective Reinforcement Learning for Generating Covalent Inhibitor Candidates

⋅

Rational design of covalent inhibitors requires simultaneously optimizing multiple properties, such as binding affinity, target selectivity, or electrophilic reactivity. This presents a multi-objective problem not easily addressed by screening alone. Here we present a machine learning pipeline for generating covalent inhibitor candidates using multi-objective reinforcement learning (RL), applied to two targets: epidermal growth factor receptor (EGFR) and acetylcholinesterase (ACHE). A SMILES-based pretrained LSTM serves as the generative model, optimized via policy gradient RL with Pareto crowding distance to […]

Ver mais

Liked Liked
Mozilla: Anthropic's Mythos found 271 zero-day vulnerabilities in Firefox 150

Mozilla: Anthropic’s Mythos found 271 zero-day vulnerabilities in Firefox 150

⋅

Earlier this month, Anthropic said its Mythos Preview model was so good at finding cybersecurity vulnerabilities that the company was limiting its initial release to “a limited group of critical industry partners.” Since then, debate has raged over whether the model presages an era of turbocharged AI-aided hacking or if Anthropic is just building hype for what is a relatively normal step up on the ladder of advancing AI capabilities. Mozilla added some important data to that debate […]

Ver mais

Liked Liked
Supreme Court arguments make it clear that FCC fines are "nonbinding"

Supreme Court arguments make it clear that FCC fines are “nonbinding”

⋅

Supreme Court justices today expressed skepticism of AT&T and Verizon’s claim that the Federal Communications Commission’s procedure for imposing fines violated their right to a jury trial. But companies regulated by the FCC may come out ahead in the long run even if the carriers lose this case. AT&T and Verizon, which were fined a total of $104 million for selling users’ real-time location data without consent, claim the FCC’s penalty system deprived them of the Seventh Amendment […]

Ver mais

Liked Liked
Silo S3 teaser hints at the wasteland's origins

Silo S3 teaser hints at the wasteland’s origins

⋅

The critically acclaimed second season of Apple TV’s dystopian sci-fi drama Silo ended on one heck of a cliffhanger, with at least one major character’s fate unclear. The streamer just released the first teaser for S3, in which events from the first two seasons rewind to give us the briefest glimpse of the lushly green, seemingly idyllic early days of the silo community, centuries before. (Spoilers for the first two seasons below.) As previously reported, Silo is based […]

Ver mais

Liked Liked
Where's the raccoon with the ham radio? (ChatGPT Images 2.0)

Where’s the raccoon with the ham radio? (ChatGPT Images 2.0)

⋅

OpenAI released ChatGPT Images 2.0 today, their latest image generation model. On the livestream Sam Altman said that the leap from gpt-image-1 to gpt-image-2 was equivalent to jumping from GPT-3 to GPT-5. Here’s how I put it to the test. My prompt: Do a where’s Waldo style image but it’s where is the raccoon holding a ham radio gpt-image-1 First as a baseline here’s what I got from the older gpt-image-1 using ChatGPT directly: I wasn’t able to […]

Ver mais

Liked Liked

Hey, I need help figuring out my rewards system for my RL Model

⋅

Hey I’m pretty new to creating AI and stuff, and at the moment I’m working on an RL AI that should play a fairly simple platform, it has just 3 inputs, right left and jump. I got everything working, capture screen make it into a matrix so the Agent can see it I got the outputs working but I don’t managed to get the rewards system to work. After a few iterations the agent stops moving, just jumps […]

Ver mais

Liked Liked
Framework's CEO on the RAM crisis and creating a "MacBook Pro for Linux users"

Framework’s CEO on the RAM crisis and creating a “MacBook Pro for Linux users”

⋅

We’ve seen enough product announcements from Framework at this point that today’s updates feel more or less routine. The biggest new thing is an updated motherboard with Intel’s Core Ultra Series 3 processors that can either be dropped into the existing Framework Laptop 13 or bought as part of the new Framework Laptop 13 Pro. Updated screens, keyboards, and other parts—mostly compatible with Framework’s existing laptops, mostly meant to address specific complaints about, or missing features in, those […]

Ver mais

Liked Liked

An AI Odyssey, Part 4: Astounding Coding Agents

⋅

AI coding agents improved greatly last summer, and again last December-January. Here are my experiences since my last post on the subject. The models feel subjectively much smarter. They can accomplish a much broader range of tasks. They seem to have a larger, more comprehensive in-depth view of the code base and what you are trying to accomplish. They can locate more details in obscure parts of the code related to the specific task at hand. By rough […]

Ver mais

Liked Liked

We open-sourced Chaperone-Thinking-LQ-1.0 — a 4-bit GPTQ + QLoRA fine-tuned DeepSeek-R1-32B that hits 84% on MedQA in ~20GB[N]

⋅

Hey everyone, We just open-sourced our reasoning model, Chaperone-Thinking-LQ-1.0, on Hugging Face. It’s built on DeepSeek-R1-Distill-Qwen-32B but goes well beyond a simple quantization — here’s what we actually did: The pipeline: 4-bit GPTQ quantization — compressed the model from ~60GB down to ~20GB Quantization-aware training (QAT) via GPTQ with calibration to minimize accuracy loss QLoRA fine-tuning on medical and scientific corpora Removed the adaptive identity layer for transparency — the model correctly attributes its architecture to DeepSeek’s original […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026