Machine Learning

It's not about generating text. What kind of AI is Jev?

Thu, 01 Oct 2026 11:33:14 +0900

Overview

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.

Jev from TypeSafe AI 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.

Evaluation of FP6 Quantization in Small-Scale Image Super‑Resolution DNNs: Condition Exploration and Comparison of Residual and Direct Generation Architectures

Thu, 24 Sep 2026 22:07:00 +0900

Overview

We compared image quality and file size when using a small image‑upscaling DNN with FP16 weights converted to FP6. In the search for optimal quantization settings, the PSNR improved on four validation images but decreased on another set of four images. Afterwards, we evaluated using 174 images divided into five groups by acquisition series, as well as 12 images that had not been used until the FP16 baseline was fixed. Even with roughly the same number of parameters, the degradation caused by uniform conversion to FP6 differed markedly between residual‑type and direct‑generation‑type models. The comparison of the 12 final FP6 images was added after viewing the FP16 results, so it does not constitute a new blind evaluation.

LLM Quantization from the Perspective of FP6: Where to Allocate Limited Bits

Thu, 24 Sep 2026 13:43:00 +0900

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.

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?

Designing a circuit to attempt machine learning with analog electronics

Thu, 13 Aug 2026 20:59:43 +0900

Last time we discussed how combining multiplication based on Ohm’s law with addition based on Kirchhoff’s current law could enable us to represent the neural network’s multiply‑accumulate operation in a physical circuit.

This time, assuming we will eventually build an actual hardware circuit, we first consider the minimal circuit configuration.

In this simulator we will keep the resistor values fixed and dynamically vary the voltage output from the microcontroller.

With this setup, the weight updates and multiplications are performed on the microcontroller side, while the analog circuit handles voltage summation and inversion. We’re not trying to implement all of machine learning with an analog circuit, but this level of setup should be sufficient for first confirming the correspondence between the equations and the circuit.

Can machine learning be implemented with analog circuits?

Wed, 12 Aug 2026 21:01:23 +0900

Wouldn’t it be interesting to do machine learning with analog circuits?

Lately, large language models have become popular, but they require a lot of GPUs, money, and electricity. I thought it would be fascinating to try doing this with analog circuits.

The calculations performed by neural networks are essentially multiplication and addition.

So, this time I’ll give a rough overview starting from the basic theory.

What is analog computation?

In digital computers, numbers are represented as combinations of 0s and 1s. Even if the voltage changes slightly during a calculation, the original information can be recovered as long as the change stays within the range where 0 and 1 can still be distinguished.