Author: Santiago Maniches
-
AI-Driven ADMET Prediction: What the Blind Challenge Results Actually Show
Deep learning beat classical methods for ADME prediction in a 65-team blind challenge at the 2025 OpenADMET competition. An AI-PBPK platform predicted full human pharmacokinetic curves from molecular…
-
Poisoning the Medical Brain: RAG Attacks and Security in Clinical AI Systems
Clinical LLMs failed prompt injection at 94% in JAMA testing. RAG systems face a harder attack: poisoned retrieved documents that the LLM cannot distinguish from legitimate sources. How…
-
RFdiffusion and ProteinMPNN: How AI Now Designs Proteins From Scratch
RFdiffusion generates protein backbones. ProteinMPNN designs the sequences that fold into them. Together they achieved sub-Angstrom accuracy at influenza binding interfaces. How the two-step pipeline works, why AI-generative…
-
What ASL-3 Actually Means: Anthropic’s Biorisk Threshold Explained
ASL-3 is Anthropic’s threshold where models could provide serious uplift on bioweapons with mass casualty potential. What the Virology Capabilities Test actually evaluates, how the 4x novice uplift…
-
DNA Synthesis Screening Cannot Keep Up With AI-Designed Sequences
The IGSC DNA synthesis screening standard was built on sequence homology to known pathogens. AI-designed sequences achieve dangerous functions through novel sequences that homology checks cannot recognize. What…
-
Evo 2: The Genomic Foundation Model Trained on 9.3 Trillion DNA Bases
Evo 2 from Arc Institute is a 40B-parameter genomic foundation model trained on 9.3 trillion DNA bases spanning all domains of life. How the 128K context architecture works,…
-
ESM3: The Protein Language Model That Unifies Sequence, Structure and Function
ESM3 from EvolutionaryScale is a 98B-parameter generative protein language model that reasons across sequence, structure, and function simultaneously. How the VQ-VAE structural tokenization works, what the GFP design…
-
AlphaFold 3 in Drug Discovery: Where It Works and Where It Fails
AlphaFold 3 predicts protein backbones well but fails significantly on ligand-binding poses in GPCR drug targets, which represent 33% of approved drugs. Five PubMed-sourced studies covering what works,…
-
Radiology Foundation Models: What Merlin, the 22% Hallucination Rate, and ED Fracture Data Tell Us
Stanford published Merlin in Nature (2026): a 3D vision-language foundation model for abdominal CT trained on 15,331 scans and over 6 million images, evaluated across 752 tasks. How…
-
AI in Radiology: Three Phases and What the Clinical Evidence Shows
Radiology AI has moved through three phases: rule-based CAD, the deep learning benchmark era, and clinical deployment validation. A 556-paper bibliometric analysis and a multicenter thymus CT validation…
-
AI in Veterinary Medicine: What the Clinical Evidence Actually Shows
Veterinary AI is producing measurable results in canine radiology, equine PET imaging, gait analysis, and dairy herd monitoring. Six PubMed-indexed studies from 2024-2026 with specific accuracy numbers, and…
-
Prompt Injection Succeeds 94% of the Time Against Clinical LLMs
A JAMA Network Open study found prompt injection attacks succeed 94.4% of the time against clinical LLMs, including 91.7% in high-harm pregnancy drug scenarios. Based on PubMed-indexed research,…
-
How Protein Language Models Learned to Design Dangerous Proteins
Researchers used three open-source protein design models to bypass DNA synthesis screening in 2025. Here is how protein language models work, why training data exclusion fails as a…
-
LLMs Give Novice Biologists 4x Uplift on Dangerous Tasks
A 2026 study measured LLM access giving novice biologists a 4.16x accuracy boost on biosecurity-relevant tasks, including beating expert baselines. Here is the mechanism and what it means…
-
How Stalkerware Bypasses End-to-End Encryption
Stalkerware captured 86,859 screenshots from a celebrity’s phone, including WhatsApp messages. Here is how it defeats encryption and what you can do about it.
-
MiniMax M2.7 Optimized Its Own Training Harness 100 Times. Here Is the Loop.
MiniMax M2.7 ran an internal agent that modified its own training scaffold 100 times in a row without human input and gained 30% on internal evaluations. Here is…
-
M-Trends 2026: Exploits Now Arrive Before Patches. The Mean Time-to-Exploit Is Negative 7 Days.
Mandiant M-Trends 2026 documents a mean time-to-exploit of negative 7 days. 28.3% of CVEs are being exploited within 24 hours of disclosure. Here is the AI attack chain…
-
KellyBench: 8 AI Models Bet the Premier League. All Lost Money.
General Reasoning put 8 frontier AI models through a full Premier League season with a 100k bankroll each. Every model lost money. The benchmark reveals three distinct failure…
-
DeepSeek V4’s Hybrid Attention Cuts KV Cache by 10x. Here’s the Architecture.
DeepSeek V4-Pro processes one million tokens using 10% of the KV cache V3.2 needed. The mechanism is Hybrid Attention: two complementary compressors interleaved across 61 layers. Here’s how…
-
WebMCP Is Not MCP: What Chrome’s modelContext Actually Ships
Chrome 146 shipped navigator.modelContext in February. It looks like MCP in a browser. It is not. Wire protocol, auth model, and security all differ.
You must be logged in to post a comment.