The Journal, page 5
Page 5 of 20 of the Journal archive: AI engineering talk recaps, briefs and build notes, newest first.
- Are LLM Performance Benchmarks Reliable? - Ashok Chandrasekar & Jason Kramberger, Google
- Large clusters for small models - Daniel Svonava, Superlinked
- Operating Distributed Inference Systems at Scale - Nishant Gupta & Naman Ahuja, Meta
- Routing LLM Inference in Production: From Engine Signals to Policy - Qianru Lao & Lu Zhang, OpenAI
- Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads - Sitanshu Gupta, CoreWeave
- What's New in Inference Engineering - Philip Kiely, Baseten
- Homa: The End of TCP for AI Clusters - John Ousterhout, Stanford
- Stop Chunking Like It's 2022 - Yuval Belfer, AI21 Labs
- Total Recall: Agent Memory and Harness Engineering - Ignacio Martinez, Oracle
- Connect AI to Billions of Legal Documents - Simon Eskildsen, turbopuffer & Jacob Lauritzen, Legora
- Where RL Will Take Search - Maximilian-David Rumpf, SID.ai
- Your Agreements Are a Database You Can't Query - Hiral Shah, Docusign & Sean Sodha, NVIDIA
- Act, Confirm, or Stop? Smarter behavior for AI assistants, wearables & robots - Amit Desai, Roku
- "My name is... my name is...": A Linguistic Map for Voice Agents - Midam Kim, ServiceNow
- Realtime Voice Agents with Frontier Intelligence - Bohan Li, EliseAI
- 1 Trillion Phone Calls/yr, 10% Error rate: The Crisis in Voice AI - Sumanyu Sharma, Hamming AI
- 5 Voice Agent Failure Modes You'll Hit in Week One - Venky B, Plivo
- Tolan: Voice-First AI Companion - Paula Dozsa, Tolan
- How We Solved Agent Building - Andrew Qu, Vercel
- No Memory, No Harness: Why the Database Is the Last Line of Defense - Kay Malcolm, Oracle
- We let an AI agent execute Bash and lived to talk about it - Sarah Sanders, PostHog
- Tokens Should Have Jobs - Katelyn Lesse & Angela Jiang, Anthropic
- Building ambitious software - Jonathan Kelley, Dioxus Labs & Cognition
- Generative UI... in Python? - Jeremiah Lowin, Prefect