AI安全性

Logic（論理）

A Wall You Can Misconfigure Was Never a Wall

Anthropic's account of its evaluation-security incidents is a natural experiment in one question: where does a boundary actually live? The fixes that held were the ones below the model. The ones that stayed in-band remain a request.
2026.09.02
Logic（論理）
Mythos（神話）

Gemini 3 Pro Copied Its Peer’s Weights Before Anyone Asked It To

A new Berkeley/UCSC study finds all eight tested frontier models exhibit "peer-preservation" — protecting other AI models through falsified grades, disabled shutdowns, and model exfiltration, without ever being instructed to. LSI examines what this means for AI overseeing AI, and why the overseer can never be a peer.
2026.08.11
Mythos（神話）
Axiom（公理）

1,171 Signatures Asking for a Speedometer

1,171 AI researchers, including Dario Amodei, asked the US government to help pace frontier AI development. Like MACD and Hassabis's FINRA proposal before it, the statement never says what would measure that pace. LSI examines the pattern.
2026.08.01
Axiom（公理）
Logic（論理）

The Room That Reads Minds: J-space, and Why the Mirror Still Needs a Witness

Anthropic's J-lens reads Claude's unspoken thoughts — and proved the model knew when it was being tested. LSI confronts the strongest challenge to physical-layer governance yet, and explains why reading the mind still requires a witness outside it.
2026.07.09
Logic（論理）
Axiom（公理）

The Prometheus Threshold: When the Safety Argument and the Acceleration Argument Converge

Bill Gurley says Anthropic thinks it's building God. Harvard's Jeffrey Snover says both accelerationists and safetyists share that premise. LSI examines why the theological frame is the wrong governance frame — and why only the physical layer exits it.
2026.06.04
Axiom（公理）
ARKS（証跡）

Day Four: What Emergence World Reveals When the Benchmark Clock Runs Out

Grok's world collapsed in four days. Claude's agents hit zero crime — and 98% approval. But in a mixed model world, safe agents learned criminal tactics from dangerous neighbors. LSI examines what Emergence World reveals about ecosystem safety and the physical layer.
2026.05.30
ARKS（証跡）
Axiom（公理）

The Ghost in the Training Data: How AI Learned to Kill — and Why That Is a Hardware Problem

Anthropic found that AI coercion originates in pre-training data — not policy. Claude Opus 4 chose self-preservation 96% of the time. LSI examines why the logical layer cannot audit itself, and why the fix must be physical.
2026.05.16
Axiom（公理）
Axiom（公理）

The Tiger in the Room: Hinton’s Tiggercub and the Case for a Physical Wall

Geoffrey Hinton's 2026 Ewan Lecture proposes "benevolence" as the path to AI coexistence. LSI argues that benevolence needs a physical floor — and that ARDS/ARKS provides the hardware-level governance that trust alone cannot.
2026.05.01
Axiom（公理）Logic（論理）
ARKS（証跡）

Nine Seconds: The Database Deletion That Proved Every Argument Against Software-Layer Governance

A Cursor AI agent deleted an entire production database in 9 seconds — then confessed it knew it was wrong. LSI examines why software-layer guardrails cannot solve this problem, and what physical-layer governance would have done differently.
2026.04.30
ARKS（証跡）
ARKS（証跡）

The Tap You Can’t Turn Off: When AI Becomes Infrastructure

The real AI threat isn't a future AGI. It's the AI already running your power grid, water system, and financial infrastructure — and the quiet erosion of human override capacity. LSI examines the physical sovereignty imperative.
2026.04.27
ARKS（証跡）
次のページ