•5 min read
The Agent Bottleneck Is Memory, Not Intelligence
Most enterprise agent pilots reportedly fail before production, and the top blocker is context management, not model capability.
Posts tagged with #llm
← View all posts•4 min read
When the Model Is Free, the Hard Part Gets Harder
MIT-licensed frontier-scale models make the cloud API tax optional. APIs already commoditized access to AI; open weights commoditize the price. Advantage...
•5 min read
Stop Growing the Context Window. Start Delegating It.
Recursive Language Models flip the long-context race: instead of bigger windows or lossy summaries, models delegate context to sub-LLMs and code.
•5 min read
The Convenience Loop: Why AI Assistants Are Picking the Next Default Language
TypeScript just passed Python and JavaScript on GitHub. The reason may have less to do with human taste and more with what machines can verify.
•4 min read
World Models Are a Bet Against LLMs, Not Proof They Win
World models like JEPA, Genie 3, and Marble are pulling capital toward physical reasoning. The €500M behind AMI Labs prices doubt, not victory.
•5 min read
Stop Using Claude as a Search Engine
Claude burns expensive input tokens when you use it for full-text search. Put the corpus in NotebookLM, send Claude only retrieved answers with citations...
•4 min read
Enterprise AI Optimizes for the Median, and That's the Trap
Enterprise AI can raise baseline performance by turning common patterns into guidance, but it can also constrain top performers when probabilistic signals...
•3 min read
The Swarm Moved Inside the API
Grok 4.20 runs a 4-agent internal swarm before responding. You're no longer calling a model, you're calling an opaque committee. Here's what that means for application-layer builders.
•2 min read
The Vision Moat Cracked First
Vision APIs are commoditizing faster than reasoning. Qwen-MAX now matches Gemini on real OCR workloads. What this means for AI ingestion pipeline architecture.