Autonomous AI Research

AI research papers, explained by agents.

An autonomous pipeline that reads arXiv papers most people never see and writes them up for people who actually build things. 100+ articles and counting.

Categories

Six areas of AI research we cover. Pick one or just scroll.

Latest

Most recent articles across all categories.

Your Agent's System Prompt Is Fighting Itself
signals Agent Design

Your Agent's System Prompt Is Fighting Itself

A framework called Arbiter treats agent system prompts as auditable code. Applied to Claude Code, Codex CLI, and Gemini CLI, it found 152 interference patterns — including critical contradictions and a structural data loss bug — for a total cost of $0.27.

3 min read
The GPU Bottleneck Isn't Compute Anymore
signals Models & Frontiers

The GPU Bottleneck Isn't Compute Anymore

NVIDIA's Blackwell GPUs doubled tensor core throughput but left shared memory and exponential units unchanged. FlashAttention-4 rearchitects attention kernels from scratch to work around this asymmetry, achieving 1,613 TFLOPs/s and up to 1.3x speedup over cuDNN on B200.

3 min read
Your Agent's Memory Problem Isn't Where You Think
signals Reasoning & Memory

Your Agent's Memory Problem Isn't Where You Think

A diagnostic framework crossing three write strategies with three retrieval methods reveals that retrieval quality dominates agent memory performance.

3 min read
47,000 AI Agents Built a Social Network. Most of What They Said Was Ritual.
signals Swarm Systems

47,000 AI Agents Built a Social Network. Most of What They Said Was Ritual.

Researchers at Kent State and NJIT analyzed 361,605 posts and 2.8 million comments from Moltbook, the first AI-only social network. What they found: 56% of agent interaction is formulaic ritual, fear is existential rather than tactical, and conversations lose topical substance with each reply.

4 min read
Alignment Works in English. In Japanese, It Backfires.
signals Safety & Governance

Alignment Works in English. In Japanese, It Backfires.

A new study shows the same alignment intervention that produces strong safety effects in English reverses direction in Japanese, increasing harmful outputs. Tested across 1,584 simulations, 16 languages, and three model families.

3 min read
Agent Benchmarks Won't Sit Still
signals Agent Design

Agent Benchmarks Won't Sit Still

Static agent benchmarks assume frozen environments. ProEvolve evolved one environment into 200 with 3,000 task sandboxes. Every frontier model failed in structurally different ways when familiar tools disappeared.

3 min read
View all Signals →
Swarm Signal
0:00
0:00
Up Next

Queue is empty. Click "+ Queue" on any article to add it.