62.7 and 99.9: same model, same exam, two scores
OpenAI published 99.9% on ARC-AGI-3 for GPT-6 Astra. ARC Prize measured 62.7% the same day. The difference is the harness, and it explains why benchmark tables no longer compare models.
-
-
The Creature No Longer Waits in Line: dynamic workflows and the jump from chain to graph
Claude Code writes the orchestration script, launches a fleet of subagents, and the coordination doesn’t cost a single token. Third installment: from the loop to a graph that runs itself.
-
Google’s new SDLC, layer by layer: the framework holds, the numbers don’t
Google published a 51-page whitepaper on the new software lifecycle with vibe coding. The conceptual framework — the spectrum, Agent = Model + Harness, the factory model — is excellent. The statistical apparatus collapses at the first question. A layer-by-layer review, with all nine headline figures traced to their primary sources.
-
Inside Graphify: a code graph with no embeddings, and the benchmark row nobody reads
Graphify turns a repository into a deterministic knowledge graph with no embeddings and no LLM cost. Its benchmark is one of the best in the sector — and it contains the row that dismantles its own headline: four thousandths over a classic hybrid RRF. A technical read of the pipeline, the numbers and the defaults.
-
Two Hundred Lines and 57 Milliseconds: the experiments behind agent governance
Agent governance is usually discussed as doctrine. We took it to a test bench: a ~200-line gatekeeper, warm-forked microVMs, and four models unknowingly trying to break the rules. The numbers, the prompt-injection matrix, and the two leaks that taught us the most.
-
The Agent Forgets, the Graph Doesn’t: from loop engineering to graph engineering
Ng’s four patterns are still the right vocabulary, but the real axis in agent architecture isn’t how many agents you have — it’s where the state lives. An honest walk from loops to graphs, and what has changed since 2024.
-
The Creature That Empties Your Backlog While You Sleep: goal-driven loops and workflows in Claude Code
Loop engineering without the smoke: the anatomy of an autonomous loop, how I run mine with a GitHub board and subagents, and the Claude Code parts that make it possible.
