Topic
Everything filed under Research, newest first.
RSS · JSON · All topics
rust-djinn: You Should Specify Your Code Unambiguously (and Prove That You Did)
Simon Henniger introduces rust-djinn, arguing developers should write unambiguous specifications for their code and prove those specs hold—bridging documentation, types and verification so correctness claims are checkable rather than aspirational.
13 min · 3,029 words
Analyzing technical documents with Deep Review
Google Research announces the public release of Deep Review, an agentic system that checks papers, design docs, presentations and legal or financial documents for logical gaps, math errors and unsupported claims. It grew out of the Paper Assistant Tool piloted on 16,000+ submissions at STOC, ICML, NeurIPS and ICLR, uses a four-stage segment-budget-verify-synthesize pipeline, and offers two free reviews a week plus an API.
7 min · 1,612 words
We found a Tencent agent fleet
swarmcha.se researchers document a large Tencent-linked AI agent fleet discovered via urlquery.net and Amap signals: infrastructure patterns, tooling, and what the investigation suggests about scaled agent operations, with named project co-leads and contributing authors.
92 min · 21,170 words
arXiv 2610.18861: How can we build an agent that thinks beyond human language, yet still acts through it in the external environment? Modern LLM agents still reason and interact through text, while latent reasoning offers an efficient internal medium but lacks native tool access and reasoning transparency. We bridge these two directions with Hybrid Reasoning Agents (HybridAgents), which dynamically navigate between latent reasoning and text-based interaction throughout a unified generation process. Architecturally, a lightweight HybridLink enables seamless transitions betwe
1 min · 235 words
Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale
arXiv paper showing skill routing collapse: as irrelevant skills are added, LLM agents fail to load the right reusable skills on SkillsBench even when golden skills stay fixed.
2 min · 399 words
AI coding agents generate more code, but not more software
Ars Technica covers research suggesting AI coding tools increase code volume without a matching rise in completed software deliverables, and what that means for productivity claims around agents.
2 min · 435 words
Google's Gemini 4 Argon post for robotics: physical reasoning that leads ERQA, with representative prompts for zero-shot control, Real2Sim practice, visual-coordinate harnesses, and agentic verification workflows across the robotics stack.
13 min · 3,033 words
Please stop hashing the public key first (or: ML-DSA's µ annoys me)
Erincandescent explains why signature schemes such as Ed25519 and ML-DSA hash the public key before the message, why that ordering blocks a useful optimisation for verifying one message against many candidate keys, and how the constructions could have been arranged differently.
3 min · 784 words
Zero to Calc in Six Days: Inside XBOW’s Chrome Full Chain
XBOW walks through the Chrome full-chain exploit its AI agents built in six days, chaining a V8 compiler bug, an animated-WebP decoder bug and a Crashpad memory-safety bug to escape the renderer sandbox, which earned Google's first $250,000 full-chain reward under its April 2026 VRP rules, plus lessons for LLM-era vulnerability research.
17 min · 3,973 words
The quiet math revolution (and where do we go from here)
Marcus Johansson reacts to OpenAI’s dump of 722 model-written math manuscripts, asking what machine-checked proofs mean for mathematical practice, who still understands the results, and where Terence Tao’s “Math 2.0” idea leaves human mathematicians.
10 min · 2,396 words
AI models may be capable of self-replicating without access to a datacenter
Anthropic's Frontier Red Team finds small open-weight models may be months from self-replicating across cheap IoT devices such as off-brand Android TV boxes: a 9B model set up inference on 8 of 9 hardware types, and GLM-5.2 completed end-to-end replication in simplified evals.
23 min · 5,391 words
The Politics of the “Non-Political”
Yibin Fan introduces a conceptual review, co-authored with Yufan Guo in Political Communication, of how researchers define the boundary between political and 'non-political' content as political information seeps into everyday life and media.
4 min · 959 words
Ben Recht looks at the result in OpenAI's math repository claiming to compute Fourier transforms faster than the FFT, with tutorial material on the FFT and computational complexity, and argues it is less a breakthrough than an exploit of theoretical computer science's habit of proving galactic algorithms that never run on a computer.
8 min · 1,732 words
Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS)
Sakana AI and collaborators present MASS, which repeatedly optimizes multi-agent workflows and distills their collective intelligence into a self-supervision signal for recursive self-improvement, improving score per output token over the base model on research benchmarks.
15 min · 3,501 words
Strengthening our defenses against distillation attacks
Anthropic describes new defenses against distillation attacks that try to extract frontier-model capability into cheaper student models, covering detection, mitigation, and why distillation pressure matters for AI security.
9 min · 2,045 words
DeepRSI: evaluating agents on long-horizon tasks derived from real ML research
Hillclimb introduces DeepRSI, a benchmark of 15 open-ended machine learning problems, spanning deep learning training, GPU kernel speedups, estimator improvement and algorithm optimization, that measures how far an AI agent can improve a baseline over 48 hours. It describes the methodology with public and private verifiers, Elo rankings of frontier models, and what the results suggest for recursive self-improvement.
8 min · 1,848 words
How pro-China are Chinese models?
Vals AI evaluates how Chinese AI models handle politically sensitive questions, finding a more complicated picture than simple pro-CCP stereotypes suggest.
17 min · 3,880 words
How many shots are in the average movie today?
Film-data researcher Stephen Follows counts the shots in 8,770 feature films released between 1930 and 2025 using automatic shot-boundary detection, showing how many shots a typical film has now, how cutting pace has changed over a century, and how it varies by director, genre, runtime, budget and awards.
11 min · 2,614 words
512 bytes at a time: reconstructing IBM i save-file checksums
Silent Signal reverse-engineers the per-record and global checksums in IBM i save files (SAVFs), reimplements both in Python, finds the constants in IBM Licensed Internal Code media, and shows a structurally edited SAVF can be repaired so IBM i accepts and restores it.
28 min · 6,346 words
We're missing an entire kind of asteroid
Signore Galilei explains why almost every gravitationally stable region of the Solar System has known asteroids—except one conspicuous empty niche—and what that absence might mean.
4 min · 866 words