Generative AI Tools & Use

LM Studio added a collaborative editing canvas to its AI agent 'Bionic,' enabling direct implementation from blueprints.

• •LM Studio announced on September 23 that it added new features to its PC-based AI agent 'Bionic.'
• •The added feature is a canvas that allows users and AI to edit collaboratively.
• •This feature enables direct code implementation from blueprints or designs.

Anthropic released 'Claude Marketplace,' a platform aggregating integration tools and partner products and services for the AI service 'Claude.'

• •Anthropic released 'Claude Marketplace' on September 23.
• •The platform aggregates over 2,000 integration tools.
• •It offers features to explore products and services from partner companies.

TypeSafe AI launched Jev, a new AI model category that returns judgments without generating text, highlighting its unique characteristics and potential applications.

• •TypeSafe AI, founded by Diogo Almeida, a co-creator of ChatGPT, announced the new AI model category 'Jev' on September 15.
• •'Jev' is characterized as an AI model that does not generate text.
• •Its design, which returns only judgments rather than parsing spoken LLM output, is drawing attention.

This article highlights a case where Claude ran DOOM using multiplication processing, addressing the underutilization of NPUs in many scenarios on the latest Windows AI PCs.

• •On the latest Windows AI PCs, the NPU is the most idle processor in many scenarios.
• •Claude ran DOOM using multiplication processing.

This article introduces Jeff, a lightweight 0.8B parameter decision model fine-tuned from Qwen3.5 and Gemma 4 for zero-shot classification.

• •Jeff is a fine-tuned model based on Qwen3.5 and Gemma 4.
• •It has 0.8B parameters, making it possible to train in a home environment.
• •Inference time is approximately 30ms, and it is designed for zero-shot classification.

Claude Code's creator discusses the black-box nature of AI-generated code and explains how to distinguish between prototypes and production code.

• •Boris Charny, creator of Claude Code, addressed whether to inspect the contents of AI-generated code.
• •He explained how to distinguish quality control between prototype and production environments.
• •He introduced specific measures to maintain code quality, including his own practical examples.

Shopify has extended WebMCP support to its checkout feature, enabling browser-based AI agents to update order details and complete purchases with buyer approval.

• •Shopify has expanded the scope of its WebMCP support to include the checkout feature.
• •Browser-based AI agents can now update order details and complete purchases.
• •These operations are performed only with the buyer's approval.

A tool was released that uses WebGPU to run small language models entirely in the browser, allowing on-device comparison and benchmarking of models like PetitGPT and SmolLM2.

• •Q4 small language models can be fully executed in the browser using WebGPU.
• •Seven small LLMs, including PetitGPT and SmolLM2, can be chatted with, benchmarked, and compared on-device.
• •It reduces reliance on servers, enabling users to test AI model performance on their devices.

Ahead of its 2026 DevDay event, OpenAI is reportedly lagging in always-on consumer AI agents, with rumors of a new agent named Aeon.

• •OpenAI popularized modern generative AI chatbots but is lagging in the AI agent field.
• •The 2026 DevDay event is expected to be an attempt to regain industry leadership.
• •Rumors suggest OpenAI will announce its self-developed AI agent, Aeon.

A tool was introduced that builds AI automation from a single prompt and executes it in a visual workspace integrated with documents and tools.

• •AI automation can be built by entering just one prompt.
• •Discovered information and deliverables are aggregated in a visual workspace integrated with documents and tools.
• •Processing is executed by provider-side or user-owned agents.