https://blog.ast.moe/en/tags/llm/Recent posts: GorimuchuHugohttps://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>https://blog.ast.moe/en/blog/2026-09-24/Thu, 24 Sep 2026 13:43:00 +0900https://blog.ast.moe/en/blog/2026-09-24/<p>While researching quantization for LLMs, I found myself wondering in what situations FP8 would actually be useful. Further investigation revealed that FP6 and FP4 also exist. I became curious about how to store values in a 6‑bit format—an oddly sized width—and how much precision a floating‑point number with so few bits could actually represent.</p> <p>When you list the values representable by FP6, the spacing between adjacent numbers becomes clearly visible—a detail that is usually overlooked with the floating‑point formats we use daily. Even with the same 6 bits, the spacing changes depending on how the bits are allocated between the exponent and the mantissa. That raises the question: could we choose the representation to match the distribution of the weights?</p>