We Didn’t Build the Master Algorithm. We Built an Orchestra.
This week everyone was watching GPT-6 and Opus 5.5. What made me stop was a model that doesn’t write a single word, and it sent me back to Pedro Domingos’s The Master Algorithm.
-
-
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.
-
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.
-
56,804 skills and fewer than a hundred seats: the pruning agents are missing
An August paper proposes we stop installing skills into AI agents and start calling them by name. The idea is good and the diagnosis is better. The implementation has been on GitHub for three weeks, has two forks, and ships a package that doesn’t exist yet.
-
The bottleneck moved: AI now writes viruses that work
Sixteen bacteriophages designed by a generative model infected and killed E. coli. The danger isn’t the machine that writes genomes: it’s that the lock protecting us was on a different door, and it has spent years recognising faces.
-
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.
-
Your Runtime Has Reflexes, Not a Conscience
Agent runtimes converged on the same architecture and nearly the same price. The interesting question is no longer which one to buy: it is what the one you already have actually enforces, and where the part you have to build yourself begins.
-
The Whirlpool, the Horizon and the Stage Prop: An Emergency Guide to the Word “Singularity”
Altman says we’re already inside the singularity. We separate the three creatures sharing one label: the real singularity of physics, AI’s borrowed metaphor, and science fiction’s quantum stage prop.
-
The Seed Vault: Why I Back Open Weights (Even Though Amodei Is Partly Right)
Amodei clarifies that Anthropic never asked for open-weights models to be banned. His post is more reasonable than the headlines suggested — and even so, the real argument is elsewhere: do we want a hyper-efficient monoculture, or a seed vault?
-
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.
