Intelligence
The real test of an AI agent starts after the demo
A fluent plan is the easy part to demonstrate. Authority, retries and recovery determine whether an agent can be trusted with ordinary work.
9 min readAll stories
15 stories
Intelligence
The benchmark ends where the workflow begins
A high score is useful evidence about a defined test. An operational evaluation also has to count refusals, handovers, repeated runs and the state left behind.
9 min read
Machines
Robots at work: the case for the ordinary cart
A machine that moves supplies through a building can reveal more about useful automation than a spectacular humanoid demonstration. Its hardest problems may belong to the building and the service around it.
8 min read
Infrastructure
AI's power problem has more than one clock
Buying accelerators, connecting a building and running a useful AI service happen on different schedules. Confusing power, energy and timing makes the infrastructure argument harder to solve.
9 min read
Intelligence
The operating costs behind downloadable AI
An imagined purchasing memo promises control, privacy and zero cost from one model download. Reading its claims separately produces a more realistic deployment decision.
9 min read
Intelligence
Your documents can make an AI answer worse
A search result can be relevant, readable and obsolete. Follow a fictional support answer from the document library to the final citation to see where grounding can fail.
9 min read
Society
What the AI coding studies actually measured
The evidence has changed, but not into a universal replacement percentage. Reading the chronology reveals why tool version, task selection and the definition of output matter.
9 min read
Infrastructure
The privacy promise inside your phone still needs a boundary
Local inference can keep a request off a server. A useful privacy claim also explains cloud fallback, surrounding app behavior and what happens to the answer afterwards.
9 min read
Society
Three jobs for captions, three costs of error
A transcript's average error rate can conceal the one word that changes an instruction. Three ordinary viewing situations show why accessibility needs more than a language-model score.
10 min read
Intelligence
When the exam becomes part of the textbook
A model can know the subject, recognize the question or have encountered the answer. A credible evaluation needs to distinguish those possibilities without treating every high score as evidence of cheating.
9 min read
Infrastructure
The dangerous instruction is already in the document
The document is supposed to provide evidence. A connected assistant can mistakenly let it provide authority as well. Follow one fictional research task through that boundary.
9 min read
Society
A signed photograph can still tell a misleading story
Content Credentials can help establish a file's history. Three versions of an imaginary street photograph show why that history and the truth of a caption remain different questions.
9 min read
Intelligence
The model teaching its own replacement needs an outside examiner
Generated training examples can improve a model or gradually narrow what it knows. The difference is in the data workflow, the checks and the evidence kept outside the loop.
9 min read
Infrastructure
An agent handshake, a token and a question of authority
A common connector can make a tool discoverable and callable. The service still has to establish whose request it is, which records are in scope and what the action is allowed to change.
9 min read
Machines
The small model earns its place by knowing when to stop
A narrowly assigned model can be useful without winning every benchmark. Its deployment needs a tested stopping rule and a destination for the work it cannot reliably finish.
9 min read