The Journal, page 8
Page 8 of 20 of the Journal archive: AI engineering talk recaps, briefs and build notes, newest first.
- FinOps for AI Agents: Who Spent All the Tokens? - Tisha Chawla & Susheem Koul, Microsoft
- Give the Agent a Budget, Not a Token - Sachin Malhotra, Anthropic
- The Missing Layer: Design Taste in AI Agents - Hassan El Mghari, Together AI
- Unlock Agent Autonomy: The Runtime for AI-Native Systems - Tushar Jain, Docker
- How I automate my own job at Hugging Face using agents - Niels Rogge, Hugging Face
- The Era of Compound Engineering - Kieran Klaassen, Every/Cora
- Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards - Dan Bjornn, Lease End
- Open Source Is Dead. Long Live Open Source. - Saoud Rizwan, Cline
- Building Turbopuffer: Gergely Orosz (@pragmaticengineer ) × Simon Eskildsen (CEO)
- Compression at the Edge - NVIDIA, Unsloth, HuggingFace, Ollama
- Gadgets: Personal app vibe coding that is actually safe - Kenton Varda, Cloudflare
- Local Models: Trust, Control, Optimization - Carter Abdallah, NVIDIA
- MCP Apps: Extending the Frontier - Ido Salomon & Liad Yosef
- MCP Tasks (async): Why Aren't Any Agents Supporting Them? - Cornelia Davis, Temporal
- Teaching AI to Find Real Vulnerabilities - Prof. David Brumley, Bugcrowd
- The State of Model Routing - NVIDIA, Cognition, OpenRouter
- When Will The Benchmaxxing Plague End? - Nick Heiner, Surge AI
- Data and Environment Curation for Post-Training LLMs - Mahesh Sathiamoorthy, Bespoke Labs
- Learning on the Job: The Future of Post-Training - Raymond Feng, Applied Compute
- Scaling to Long Horizons - Ross Taylor & Chengxi Taylor, General Reasoning
- Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It - Olive Song
- fighting slop with slop - Vaibhav Gupta, Boundary
- Reinforcement Learning without Verifiable Rewards - Will Brown, Prime Intellect
- AI on Your Lakehouse: Context Comes in Shapes, Not Queries - Zach Blumenfeld, Neo4j