How an inference provider can prove they’re not serving a quantized model

← Back to Posts Feb 3, 2026•12 min read Tinfoil Team Updated Feb 21, 2026 When you call an inference API, how do you know which model you’re actually served? Sure you can specify the name of the model you expect to process your request, but ultimately you have no guarantee that the provider is […]
Meta Deployed AI and It Is Killing Our Agency

We manage millions of dollars in annual Meta ad spend. Not thousands. Millions. Our retail clients grow their businesses through Meta Ads, and for a lot of them, it’s their single most important growth channel. We are, by any reasonable definition, a high-value customer. And yet, for the past several months, Meta has been treating […]
Excessive token usage in Claude Code

Bug DescriptionStarting from today’s morning with the updated to CC 2.1.1 – the usage is ridiculous. I am working on the same projects for months, same routines, same time. But today it hits 5h limits like 4+ times faster! Holidays season had 2x usage promot, but current usage is way more then 2x. I am […]
What Is OAuth?

@geoffreylitt.com recently asked a question about OAuth on dead-Twitter: I desperately need a Matt Levine style explanation of how OAuth works. What is the historical cascade of requirements that got us to this place? There are plenty of explanations of the inner mechanical workings of OAuth, and lots of explanations about how various flows etc […]
Cord: Coordinating Trees of AI Agents

AI agents are good at doing one thing at a time. Give Claude a focused task and it performs. But real work isn’t one task. It’s a tree of tasks with dependencies, parallelism, and context that needs to flow between them. The multi-agent frameworks are multiplying. They’re all solving the wrong problem. What’s out there […]
Be Wary of Bluesky
In 2023, Bluesky’s CTO Paul Frazee was asked what would happen if Bluesky ever turned against its users. His answer: ”it would look something like this: bluesky has gone evil. there’s a new alternative called freesky that people are rushing to. I’m switching to freesky” That’s the same argument people made about Twitter. ”If it […]
CERN rebuilt the original browser from 1989

Hello, World In December 1990, an application called WorldWideWeb was developed on a NeXT machine at The European Organization for Nuclear Research (known as CERN) just outside of Geneva. This program – WorldWideWeb — is the antecedent of most of what we consider or know of as ”the web” today. In February 2019, in celebration of […]
ΛProlog: Logic programming in higher-order logic

λProlog Home Page λProlog is a logic programming language based on higher-order intuitionistic logic in the style of Church’s Simple Theory of Types. Such a strong logical foundation provides λProlog with logically supported notions of modular programming, abstract datatypes, higher-order programming, and the lambda-tree syntax approach to the treatment of bound variables in syntax. Implementations […]
Diode – Build, program, and simulate hardware

Sign InSign Up
I hate AI side projects
The best thing about AI is that EVERYONE can build now. The worst thing about AI is that EVERYONE can build now. I’ve worked on and shared many of my side projects over the years. I built them because they gave me a chance to learn new things, such as deploying my first web app […]