AI Comes for the If Statement (4 minute read)

TLDR AI News

Summary

AI models like Jev and SemIf are optimizing if-then decision-making in software, leading to significant cost reductions and improved accuracy, which highlights the potential for specializing other programming primitives.

New AI models like Jev2 and SemIf streamline the if-then decision-making process, cutting costs by 99% and improving accuracy from 47% to over 80% in tests. These advancements optimize coding primitives, potentially transforming AI's economic model by using specialized systems for production. Specialization in these models promises significant cost savings while maintaining high accuracy.
Original Article
View Cached Full Text

Cached at: 09/22/26, 02:39 PM

# AI Comes for the If Statement Source: [https://tomtunguz.com/ai-comes-for-the-if-statement](https://tomtunguz.com/ai-comes-for-the-if-statement) Working in the back of a grocery store has its own set of rules : if the food is a banana, send it to produce ; if it is a cookie, the snack aisle ; if it is cumin, shelve it with the spices\. But what if the load of bananas has spoiled, the cookies have crumbled & the cumin is caked? These rules & exceptions govern every grocery store & neighborhood mart\. At the beginning they are rigid ; over time, more exceptions are discovered : is that a plantain? Dubai chocolate : dessert or baking supply? Coding literally means encoding these rules & exceptions into software\. Pre\-AI, these programs were rigid\. AI handles the exceptions : an image search identifies the unfamiliar fruit as Musa paradisiaca, a brother of the banana\.[1](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:1) But we do not need the world’s most brilliant model to handle if\-plantain\-then\-produce logic\. The newest wave of AI is a robust if\-then decider\. Jev[2](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:2)& SemIf[3](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:3)answer questions like these in hundreds of milliseconds at a 99% reduction in cost compared to traditional AI\.[4](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:4)They simplify the existing models by running the attention math once & then determining the probability of each allowed answer, based on a few tokens of output\.[5](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:5) I went looking for the if\-then statements in my own code, the ones I had handed to AI\. Within a few minutes I had replaced about a quarter of those calls in one of my agents\. On 98 hand\-verified production email threads, the specialized deciders nearly doubled the classification accuracy of the production model, jumping from 47% to over 80%\.[6](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:6) [![Specialized deciders nearly double classification accuracy](https://res.cloudinary.com/dzawgnnlr/image/upload/w_1512,h_964,c_fill,g_auto,q_auto,f_auto/w1gandmv06am5jimt542)](https://res.cloudinary.com/dzawgnnlr/image/upload/q_auto,f_auto/w1gandmv06am5jimt542) Software is composed of primitives : the if\-then statement is one of them\. By optimizing this single primitive, we see nearly two orders of magnitude in cost reduction alongside higher accuracy\. These advances raise the question of which other programming primitives will benefit from the same specialization\. They also highlight the bifurcating economics of AI : state of the art models for discovery & optimized models for production\. We use the largest frontier models to train new models, & the most capable models to architect systems\. But once a system is engineered & hardened, running it thousands or millions of times through a workflow benefits from narrower AI\. If this is the first of many primitives specialized for production, then harnesses are about to capture a lot more margin\.[7](https://tomtunguz.com/ai-comes-for-the-if-statement#fn:7)

Similar Articles

AI is eating the AI Engineering Loop (5 minute read)

TLDR AI

The article discusses how the AI engineering loop can be fully automated but argues that handing over the entire loop produces 'agent slop' due to imperfect evals. It recommends automating certain steps while keeping human judgment for nuance.

AI, Ashby Engineering, and the future

Hacker News Top

Ashby Engineering shares that over half of their production code is now AI-generated since August 2025 with no increase in customer issues or code quality regressions. The post outlines their philosophy that AI eliminates mechanical coding tasks while engineer judgment and empathy become more valuable.