Are you paying an AI ‘swarm tax’? Why single agents often beat complex systems
New Stanford research challenges the assumption that more agents means better AI — and introduces a simple compute-budget fix that changes the calculus.
Ben Dickson
Train-to-Test scaling explained: How to optimize your end-to-end AI compute budget for inference
AI reasoning does not necessarily require spending huge amounts on frontier models. Instead, smaller models can yield stronger performance on complex tasks while keeping per-query inference costs manageable
Ben Dickson
Meta researchers introduce 'hyperagents' to unlock self-improving AI for non-coding tasks
Creating self-improving AI systems is an important step toward deploying agents in dynamic environments, especially in enterprise production environments, where tasks are not always predictable, nor consistent.
New framework lets AI agents rewrite their own skills without retraining the underlying model
A multi-university research team built a framework that teaches agents to fix their own failure modes — no human intervention required.
Ben Dickson
Meta's new structured prompting technique makes LLMs significantly better at code review — boosting accuracy to 93% in some cases
This technique can be used out-of-the-box, requiring no model training or special packaging. It is code-execution free, which means you do not need to add additional tools to your LLM environment.
Ben Dickson
IndexCache, a new sparse attention optimizer, delivers 1.82x faster inference on long-context AI models
The technique works by detecting that adjacent model layers repeat the same token selections — then caching the result instead of recalculating.
Ben Dickson
How xMemory cuts token costs and context bloat in AI agents
New research technique xMemory cuts token usage nearly in half for multi-session AI agents by replacing flat RAG with a four-level semantic hierarchy.
Ben Dickson
Three ways AI is learning to understand the physical world
LLMs can't reason about physics. World models might — and three distinct architectural approaches are competing to fill that gap.
Ben Dickson
Nvidia says it can shrink LLM memory 20x without changing model weights
Nvidia's KVTC compresses LLM memory 20x without model changes, cutting latency 8x for coding assistants and agentic workloads.
Ben Dickson
Google finds that AI agents learn to cooperate when trained against unpredictable opponents
Google finds diverse opponent training beats hardcoded orchestration for getting AI agents to cooperate in enterprise deployments.
Ben Dickson
New KV cache compaction technique cuts LLM memory 50x without accuracy loss
Enterprise AI hits a memory ceiling with long documents and complex tasks. MIT's new Attention Matching compresses the KV cache by 50x without accuracy loss — in seconds, not hours.
Ben Dickson
Microsoft's new AI training method eliminates bloated system prompts without sacrificing model performance
Microsoft's new OPCD framework trains AI models to internalize long system prompts directly into their weights, cutting inference overhead without losing general capability.
Ben Dickson