Cognition's FrontierCode 2.0 Reveals Every AI Coder Fails Half of Real Engineering Tasks

Cognition's new coding benchmark tests whether agents respect unstated constraints, with top model Opus 5.5 scoring just 45% on tasks maintainers built over 40+ hours each.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-27 17:24 · AlphaSignal
Cognition's FrontierCode 2.0 Reveals Every AI Coder Fails Half of Real Engineering Tasks

More stories

Apple Creator Studio update adds MotionVFX to Final Cut, and AI to everywhere — Engadget
Frontier AI labs say their models refuted the Exponential Time Hypothesis. What does that mean? — TechCrunch AI
DeepMind unveils Genie 4 world model promising more realistic physics and humans — Ars Technica AI
Introducing GPT-6.1 Terra — OpenAI News
Meta announces $95B offering to fund AI — Semafor Technology
Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock — AWS Machine Learning Blog
Microsoft to reportedly offer buyouts to 60,000 employees in latest cuts — The Guardian AI
Anthropic's IPO filing shows soaring sales and steep losses — France 24 — Artificial Intelligence

Get the daily brief of stories like this at 6:30 every morning →