Web Search in the OpenAI Prompts Playground remains restricted for some models and disabled for others. With the addition of MCP support however, users may add other Web Search providers, e.g. Exa. Exa’s (remote) MCP server does not support the complete functionality of the Exa API, but setup is straightforward: Sign up Retrieve API key A... Read more 30 May 2025 (Updated) - 4 minute read
Anthropic released Claude 4 Opus and Sonnet last week. Per the benchmark results they have published, Claude 4 Opus is roughly comparable to OpenAI o3. However, the updated Aider LLM Leaderboard places Claude 4 Opus on par with o4-mini, at a substantially higher cost. While Anthropic claims that “Claude Sonnet 4 is a significant upgrade to Claud... Read more 27 May 2025 - 1 minute read
In discussions about the regulation of AI services under European law, ChatGPT is in focus — this time concerning the Digital Services Act (DSA). Prompted by a commentary by Luca Bertuzzi on MLex, a LinkedIn exchange recently debated whether ChatGPT qualifies as a “Very Large Online Search Engine” (VLOSE) under the DSA framework. My contribution... Read more 14 May 2025 - 2 minute read
The Model Context Protocol (MCP), dubbed “USB-C for AI”, but essentially an out-of-process execution variety of the tool-use paradigm originally by Anthropic, has raised security concerns before. Now, a blog post finds that the official Python SDK makes MCP server services available to the world (0.0.0.0), not just locally (127.0.0.1). As a resu... Read more 13 May 2025 - 1 minute read
In a recent LinkedIn discussion around a review of PDF-focused KI-Assistants (ComputerBase article), I touched on limitations, workarounds, and the ongoing tension between domain-specific tooling and general-purpose, ever-evolving AI platforms. The Article in Brief The ComputerBase article put Adobe’s new KI-Assistant, Google’s NotebookLM, and... Read more 12 May 2025 - 3 minute read