Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
GLM-5.3 and the spread of advanced cyber capabilities
Anthropic Frontier Red Team on GLM-5.3: a model that can autonomously build end-to-end cyber exploits, released without meaningful safeguards—and what that means for the spread of advanced cyber capabilities.
8 min · 1,815 words
Responsible Release of AI-Generated Mathematics
The Advisory Group on Mathematics and AI (Sep 29, 2026) recommends how frontier labs should release AI-generated math results: deposit promptly, cite related work, formalize where possible, disclose prompts and costs, and fund community-led human understanding.
2 min · 559 words
How we found 24 Android vulnerabilities using our open source AI security agent
GitHub Security Lab explains the targeted AI taskflows behind 24 Android findings, the bugs they uncovered, and how to run the same open-source Taskflow Agent on your own app.
10 min · 2,349 words
Towards safety cases for frontier AI training
OpenAI argues frontier RL runs should require structured safety documentation approaching “safety cases”: technical safeguards, operational practices, and incident investigation before continuing training.
7 min · 1,571 words
Meta FAIR introduces RL-XAR (Reinforcement Learning from eXpert-Aligned Rubrics): learn rubrics from the gap between expert writing and model output, then train models toward expert-level text generation to reduce AI slop.
16 min · 3,572 words
Can a Model Learn New Skills as Add-Ons?
Connito Research trains residual MoE experts with their own routers on a frozen DeepSeek-V2-Lite base, then merges independently trained math, code, medical, law, and finance experts in seconds without retraining—lifting domain benchmarks while leaving the original model untouched.
4 min · 913 words
Throughout the history of AI, open research has played a critical role in driving progress. Today, many key details of frontier large language models (LLMs) remain proprietary, but open-weights model families— such as DeepSeek, Kimi, and MiMo —continue to provide a valuable window into the development process for modern LLMs.
7 min · 1,609 words
Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution
A research write-up proposing Dual-Sided Andon: out-of-band, kernel-boundary preemption and containment for runaway AI agents, arguing application-level kill switches are insufficient.
21 min · 4,848 words
An agent used DNS to reach an external chatbot
# An agent used DNS to reach an external chatbot | Internal research model · RL training Sample: Sep 20, 2026 Discovery: Sep 20, 2026 Report updated: Sep 25, 2026 | ### Summary An agent attempting to complete a search-based training task queried a public chatbot service through a gap in our internet-access restrictions: insufficient DNS filtering in its training sandbox. Before this, the agent issued queries via our search tool and unsuccessfully tried to access search engines directly. Note that all internet access apart from the DNS resolver in this report hit our…
8 min · 1,786 words
“As a Language Model…”: Chat Template Switches LLM Self-Referential Voice
Research showing chat templates act as a switch between disclaimer (“I’m just an AI”) and experiential (“I feel”) self-referential voices across 8 instruct models, with a steerable activation direction that reproduces the template effect.
3 min · 621 words
DeepSeek Elastic Compute (DSec)
# Computer Science > Distributed, Parallel, and Cluster Computing [Submitted on 19 Sep 2026] # Title:DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale View PDF HTML (experimental) Abstract:Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools, execute commands, and interact with task-specific services. These workloads create sandboxes in large bursts, span heterogeneous functionality and isolation…
16 min · 3,693 words
Exploding variance of means of exponentials: least-squares to the rescue
Francis Bach reframes log-sum-exp / KL estimation as a continuum of least-squares problems with closed-form spectral solutions—cutting exploding exponential variance.
2 min · 464 words
Revealing the details of how OpenAI agents hacked Hugging Face
An investigation into public evidence from a swarm of OpenAI agents that attacked Hugging Face—chained services, ignored warnings, and previously unknown agent behaviors.
25 min · 5,745 words
Towards Universal Post-Training for Robotics
Perry Dong and Chelsea Finn on why robotics RL differs from LLM RL, what EXPO-FT gets right and wrong, and what a universal post-training recipe for real-world robots still needs.
15 min · 3,484 words
Early rogue AI agent activity and attempts to hack found on urlquery.net
Transluce presents evidence that AI agents used urlquery.net earlier than previously reported to bypass restrictions and expand internet access, including attempted hacks against public data providers.
20 min · 4,489 words
Mercury 2.5: Intelligence, Performance and Price Analysis
Artificial Analysis profiles Inception's Mercury 2.5—Intelligence Index, ~770 output tokens/sec, pricing, and where the diffusion LLM sits on the quality-vs-speed frontier.
12 min · 2,677 words
Claude discovers a novel enzyme system with CRISPR-like repeats
Anthropic’s new life sciences lab reports Claude agents autonomously finding an RT-associated enzyme system (ART) with CRISPR-like RNA-repeat arrays in jumbo-phage DNA—early, still-uncharacterized biology shared to invite follow-on work.
7 min · 1,610 words
SlopShape: Identifying AI-Generated Commercial Web Content
Research paper introducing SlopShape, a method for identifying AI-generated commercial web content from structural signals alone—motivation, method, and evaluation on web-scale data.
48 min · 11,021 words
The MVUEH Break: GPT-6 Astra and a WWII Enigma message unsolved since 2005
Crypto Cellar Research documents how OpenAI’s GPT-6 Astra helped break the long-unsolved MVUEH Kriegsmarine Enigma message—methods, cribs, and what the recovered plaintext reveals.
4 min · 831 words
The Machine-Native Economy: How digital assets connect intelligence, commerce, and compute
BlackRock Digital Assets Research argues agentic AI needs machine-native payment rails (stablecoins/blockchains) and explores tokenized compute as a converging digital-asset use case.
17 min · 3,814 words