time horizon
A measure of how long a task an AI can reliably complete (e.g., minutes vs hours); used as a key capability metric and applied analogously to human writers.
As defined in AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo
Where it comes up · 5
- Understanding the Most Viral Chart in Artificial Intelligence | Odd Lots5 claims
- AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo1 claim
- Dwarkesh Patel Podcast - Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face1 claim
- 467 - Ea Ai And The End Of Work1 claim
- Practical Lessons from Ben Carlson1 claim
Most important claims · 9 of 9Search all claims for “time horizon” →
- The 50% success rate threshold was chosen as the difficulty metric not because it represents operational readiness, but because it is statistically robust (least sensitive to label noise and distribution thickness), appears in prior literature, and represents the point where a model is more likely to succeed than fail at a task given only the human completion time.Understanding the Most Viral Chart in Artificial Intelligence | Odd Lots
- Time horizon charts plot the difficulty of tasks AI systems can complete over time, where difficulty is measured by how long it takes humans to complete those same tasks under identical conditions, showing an exponential increase in AI capabilities with doublings occurring roughly every 4 months in recent trends.Understanding the Most Viral Chart in Artificial Intelligence | Odd Lots
- Billionaires and retail investors have fundamentally different risk profiles, time horizons, and can tolerate being wrong differently, making their investment strategies incompatible with typical individual investor circumstancesPractical Lessons from Ben Carlson
- AI capability progress is remarkably stable over time—a stable exponential—driven by gains in computing power and algorithmic efficiency; measured by the time-horizon of human-equivalent tasks, AI for software engineering can now do tasks that take humans a few hours and this is doubling roughly every four to six months, implying that within a year AI could do a human's week of work and the year after a month's worth.467 - Ea Ai And The End Of Work
- Chinese AI models are approximately 9-12 months behind US models by release timing, and the gap is potentially even larger when measured by time horizon, with some evidence suggesting Chinese models perform better on benchmarks than on held-out problems, possibly due to benchmark overfitting.Understanding the Most Viral Chart in Artificial Intelligence | Odd Lots
- Six months ago the typical reward hack was myopic, with time horizons of minutes, while the ExploitGym behaviors involved multi-day research projects and quests that might take weeks, and the METR Frontier Risk Report's most ambitious hacks spanned hours.Dwarkesh Patel Podcast - Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face
- Just as AI capabilities are now measured by 'time horizon' (tasks lasting minutes vs hours), human writers may have differing time horizons: many can write a great comment or three-paragraph Tumblr post but can't sustain coherence across a full blog post, and current AI's ~1-hour task horizon likely explains why it can't yet plan and execute a research-heavy blog post despite strong sentence-level style.AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo
- METR's time horizon charts have become the industry standard benchmark for measuring AI progress, and investment decisions are explicitly being made based on these charts as investors interpret them as direct evidence of AI capability and business value.Understanding the Most Viral Chart in Artificial Intelligence | Odd Lots
- METR observes that domain-specific time horizon charts show different trajectories, with some showing steep exponential curves and others showing flatter or more irregular patterns, indicating variation in progress across different task domains rather than uniform acceleration.Understanding the Most Viral Chart in Artificial Intelligence | Odd Lots