📄 文章列表

24 篇文章
AlphaSignal

Anthropic's Claude Fable 5.2 Beats GPT-6 Astra With a Rare Five-Point Jump

❌ failed ⭐ ☆☆☆☆☆ 2026-11-09
AlphaSignal

Epoch's IPI Shows Nvidia GB300 Delivers 25x an H100's Real Inference Capacity

❌ failed ⭐ ☆☆☆☆☆ 2026-11-09
AlphaSignal

Epoch Rebuilds Its ECI Leaderboard With Bayesian Stats to Sharpen AI Rankings

✅ completed ⭐ ☆☆☆☆☆ 2026-11-04
AlphaSignal

Sakana AI Bets on Sawara to Build Agent-Native Models From Scratch

✅ completed ⭐ ☆☆☆☆☆ 2026-11-02
AlphaSignal

Epoch's GLM 5.3 Built Real Firefox Exploits From Public Patches for $1,000

✅ completed ⭐ ☆☆☆☆☆ 2026-10-29
TDS

Mathematical Experiments Are Becoming Abundant Through Human-Machine Teaming

✅ completed ⭐ ☆☆☆☆☆ 2026-08-15
AlphaSignal

Epoch's FrontierMath Benchmark Cracks a 40-Year-Old Math Problem Using Fable 5 | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-27
AlphaSignal

Epoch Finds AI Detectors Miss 26% of Scientific Writing Disguised as Human | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-18
AlphaSignal

Epoch's MirrorCode Benchmark Shows Claude Opus 4.7 Rebuilding Software Autonomously in 14 Hours | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

Epoch's EBR-Bench Shows GPT-5.5 and Claude Can't Learn From Practice | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

Epoch Finds OpenAI's Codex Engineers Now Ship 4x More Superhuman Workdays | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

Anthropic's Claude Mythos Triggers a 3.5x Record CVE Spike | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

Epoch Expands its ECI to 65 Benchmarks as Classic AI Evals Die | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-01
AlphaSignal

Epoch's MirrorCode Benchmark Shows Claude Opus 4.7 Rebuilding Software Autonomously in 14 Hours | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

Epoch Caught 42% of FrontierMath Problems Broken, Sending GPT-5.5 Scores Soaring | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

Epoch Builds a Free Dashboard Tracking How Claude Mythos Is Flooding CVE Reports | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

Epoch Finds Open-Weight AI Models Trail Closed Frontier by Four Months | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

Epoch Caught 42% of FrontierMath Problems Broken, Sending GPT-5.5 Scores Soaring | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

Epoch Builds a Free Dashboard Tracking How Claude Mythos Is Flooding CVE Reports | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

Epoch AI Warns Token Demand Is Outpacing Global GPU Supply by 10x | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27