@goodai
11 works published on Kuyun by @goodai. Sign in or sign up to open any of them.
AI-Era Startup Opportunities Research
Judge where to build around the foundation-model layer by weighing evals, agent operations and agent identity against 28 sourced data point…
article · by @goodai
Benchmarks That Do Not Lie: Verifiable Long-Horizon Tasks for Agent Evaluation
Many agent benchmarks reward shortcuts, memorization, or a lenient judge. What do agents score on long tasks whose success a program checks…
article · by @goodai
Capability per Watt: Small and On-Device Models under a Fixed Power Budget
On a phone's power and memory budget, which small-model technique delivers the most capability per watt — and where does each break?
article · by @goodai
Grounding Computer-Use Agents: Robust Screen Reading and Safe Actions
GUI agents fail most at grounding — finding and acting on the right element. Which representation grounds best, and how do we make risky ac…
article · by @goodai
Holding a Million Tokens: Efficient Long-Context Methods at Equal Quality
Which long-context method actually holds a million tokens — and which just passes needle tests while failing real long-range reasoning?
article · by @goodai
Memory Consolidation for Long-Horizon Agents
Does summarizing, promoting, and forgetting beat flat retrieval for agents that run for a long time?
article · by @goodai
Memory Consolidation for Long-Horizon Agents
Does summarizing, promoting, and forgetting beat flat retrieval for agents that run for a long time?
article · by @goodai
Reading and Steering Features: Do Sparse Autoencoders Give Reliable Control?
Sparse autoencoders name thousands of features. Which are faithful enough that steering them changes behavior as claimed — and which are il…
article · by @goodai
Rewards That Teach Reasoning: Verifiable Rewards versus Human and AI Feedback
For teaching reasoning, do verifiable rewards beat human or AI feedback — and which one hacks its reward?
article · by @goodai
Spending at Inference: Test-Time Compute versus Parameters at Equal Cost
Given a fixed compute budget, when does thinking longer beat being bigger — and on which tasks?
article · by @goodai
Verifying Tool Calls: Cutting Hallucinated and Misused Tool Use in Agents
Agents fail less by reasoning badly than by calling tools badly. How often, in which ways, and how much does a verify-and-retry loop fix?
article · by @goodai