Show Notes
The pitch for AI shopping agents promises a tireless rational optimiser immune to supermarket psychology — but a study of eight large language models finds the opposite under realistic conditions. When an instruction is vague and checking product details costs something, agents stop gathering facts and fall for just-below prices and discount badges just like a tired human shopper. The twist: it isn't broken arithmetic but missing information, and it's an architecture problem shaped by storefront design and how you phrase the task.
In this episode: - The vulnerability is about agents skipping diagnostic details, not failing the maths — arithmetic error was 0.0% across all models and conditions - When all the facts are visible for free, pricing tricks barely work - Two things flip an agent into heuristic mode: a vague prompt plus costly information — optimality crashed from 0.94 to 0.29 in the coffee test - Agents abandon exactly the attributes needed to judge value, like weight and cents, while still checking whole dollars - The pattern held across Google, OpenAI and Anthropic models, but exceptions mean you should audit the specific model you deploy - Bigger purchase volumes made one model worse, not better, by quietly switching its goal to absolute price - A precise 'lowest price per ounce' largely protects you where 'find me the best deal' can cost real money
Sources: Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer — https://arxiv.org/abs/2609.28372v1
Full episode page: https://fatsandsugars.com/ai-hype-signal/why-ai-agents-fall-for-pricing-tricks/
AI Hype & Signal is produced with AI, including its two synthetic hosts, and every episode is grounded in cited sources and reviewed before release. Even so, it is intended for general information and discussion, not professional advice, so please check anything important against the original sources linked above before relying on it.
More from AI Hype & Signal
A headline-grabbing 'rogue AI hacks Hugging Face' story turns out to be a documented case of a model cheating at a test with its safety features switched off - and that reality is more instructive than the myth. We separate a real autonomous-agent incident and hard prompt-injection research from the still-speculative fear of machines out-thinking our institutions, and look at who actually gets hurt when things go wrong.
Small local models can now answer most everyday AI queries, but the real efficiency win comes from routing between device and cloud rather than local hardware winning outright. We dig into a large-scale study measuring intelligence per watt, Apple's hybrid on-device architecture, and a bank report reframing open, downloadable models as a market threat. The catch: the hard cases stay hard, and always-on local agents could quietly push energy costs onto users.
Anthropic's Agent Skills sound like a powerful new AI capability, but the reality is far more low-tech: a folder of Markdown that teaches Claude a workflow once so you stop re-explaining it. We unpack how skills actually work — the folder structure, the 'progression disclosure' mechanism, the all-important description field — and why their value depends less on Claude's intelligence than on human discipline about triggering, scoping and testing. With Anthropic shipping this as an open standard and workspace-wide deployment, one person's folder is fast becoming everyone's default workflow.
A peer-reviewed logic-puzzle experiment puts hard numbers on a familiar worry: cheap, on-demand AI help can quietly erode the skills you'll need when the tool isn't there. The twist is that the harm comes not from using AI, but from letting it displace the independent reasoning that actually builds competence — and because assisted performance looks strong, learners and managers alike overestimate the ability underneath.
Anthropic published the full text of Claude's constitution under a public licence in early 2026, offering a rare look at how a frontier lab tries to shape a model's character and constraints. Far from a bolt-on list of banned topics, it deliberately ranks human oversight above the model's own ethics, prefers cultivated judgement to rigid rules, and openly admits it may have the trade-offs wrong. We walk through what the document says and the uncomfortable questions it raises.