https://blog.ast.moe/en/tags/jev/Recent posts: GorimuchuHugohttps://blog.ast.moe/en/blog/2026-10-09/Fri, 09 Oct 2026 10:03:32 +0900https://blog.ast.moe/en/blog/2026-10-09/<p>In the previous article (<a href="https://blog.ast.moe/en/blog/2026-10-08-3/">source</a>), we introduced Izanagi, which isolates and runs development commands while recording file accesses and network communications. This time, we discuss the addition of behavior analysis using Jev.</p> <p>Existing detection rules issue warnings based on a single action—such as an attempt to open a secret file, a connection to an address outside the allowed list, or the execution of an unexpected command. In addition, we have made it possible to link multiple actions together in chronological order.</p>https://blog.ast.moe/en/blog/2026-10-01/Thu, 01 Oct 2026 11:33:14 +0900https://blog.ast.moe/en/blog/2026-10-01/<h2 id="overview">Overview</h2> <p>Even if you encounter the name “Jev,” it’s not immediately clear whether it’s an AI that answers questions in chat, a search model, or a scaled‑down version of an existing large language model. I myself built a MCP server that uses Jev, but knowing how to call its API and understanding its return values are separate issues.</p> <p> <span> <a target="_blank" href="https://docs.typesafe.ai/introduction"> Jev from TypeSafe AI </a> <img class="external-link-icon" src="https://blog.ast.moe/images/outer-link.png" width="12" height="12" alt="" aria-hidden="true" loading="lazy"> </span> is a model that, given input information, returns a judgment on predefined questions. Rather than producing free‑form explanatory text, it returns values suitable for programmatic handling—such as the probability of a “yes” answer, probabilities for each candidate, tiered ratings, and so on. For example, you feed it a query text and have it evaluate whether it concerns an invoice inquiry, a shipping inquiry, or whether it needs to be routed to a specific person. Rather than reading the answer and continuing the conversation, the usage is that the code receiving the answer decides the next action to take.</p>https://blog.ast.moe/en/blog/2026-09-26-3/Sat, 26 Sep 2026 20:30:00 +0900https://blog.ast.moe/en/blog/2026-09-26-3/<p>I often see people treating search, classification, comparison, and judgment as tasks that can simply be handed off to an LLM. If you ask it in natural language, you get a response, and you can keep asking follow‑up questions directly. That convenience is indeed useful, and I’m prone to entrusting everything to it. As a result, it’s easy to develop an impression that an LLM can solve any problem.</p> <p>On the other hand, even when using a judgment model like Jev, you can still give it tasks that aren’t suited for it. Asking it to hunt for information before the necessary data has been gathered, or to have it formulating an overall strategy before any candidates have been identified, is asking a limited‑purpose decision‑making tool to perform investigative work as well. If you only need to locate known terms, you can simply perform a string search without invoking a model at all.</p>