techxiv
How we reduced the size of our Agent Go binaries by up to 77% - How we reduced the size of our Agent Go binaries by up to 77%
How Stably ships AI testing agents in hours, not weeks - How Ramp kept 100% uptime through 100x traffic surges on Vercel
GPT-5.2 derives a new result in theoretical physics - Scaling social science research
- Beyond rate limits: scaling access to Codex and Sora
Balancing cost and reliability for Spark on Kubernetes 
The Death of Traditional Testing: Agentic Development Broke a 50-Year-Old Field, JiTTesting Can Revive It - Harness engineering: leveraging Codex in an agent-first world
Results from the Advent of FPGA Challenge - Building Prometheus: How Backend Aggregation Enables Gigawatt-Scale AI Clusters
Accelerating Mathematical and Scientific Discovery with Gemini Deep Think - Anyone can build agents, but it takes a platform to run them
- How we built AEO tracking for coding agents
- GPT-5 lowers the cost of cell-free protein synthesis
Building a C compiler with a team of parallel Claudes - Quantifying infrastructure noise in agentic coding evals
- Building a C compiler with a team of parallel Claudes
- Quantifying infrastructure noise in agentic coding evals