Friday, 22nd August 2025
too many model context protocol servers and LLM allocations on the dance floor. Useful reminder from Geoffrey Huntley of the infrequently discussed significant token cost of using MCP.
Geoffrey estimate estimates that the usable context window something like Amp or Cursor is around 176,000 tokens - Claude 4's 200,000 minus around 24,000 for the system prompt for those tools.
Adding just the popular GitHub MCP defines 93 additional tools and swallows another 55,000 of those valuable tokens!
MCP enthusiasts will frequently add several more, leaving precious few tokens available for solving the actual task... and LLMs are known to perform worse the more irrelevant information has been stuffed into their prompts.
Thankfully, there is a much more token-efficient way of Interacting with many of these services: existing CLI tools.
If your coding agent can run terminal commands and you give it access to GitHub's gh tool it gains all of that functionality for a token cost close to zero - because every frontier LLM knows how to use that tool already.
I've had good experiences building small custom CLI tools specifically for Claude Code and Codex CLI to use. You can even tell them to run --help to learn how the tool, which works particularly well if your help text includes usage examples.
Mississippi's approach would fundamentally change how users access Bluesky. The Supreme Court’s recent decision leaves us facing a hard reality: comply with Mississippi’s age assurance law—and make every Mississippi Bluesky user hand over sensitive personal information and undergo age checks to access the site—or risk massive fines. The law would also require us to identify and track which users are children, unlike our approach in other regions. [...]
We believe effective child safety policies should be carefully tailored to address real harms, without creating huge obstacles for smaller providers and resulting in negative consequences for free expression. That’s why until legal challenges to this law are resolved, we’ve made the difficult decision to block access from Mississippi IP addresses.
— The Bluesky Team, on why they have blocked access from Mississippi
DeepSeek 3.1. The latest model from DeepSeek, a 685B monster (like DeepSeek v3 before it) but this time it's a hybrid reasoning model.
DeepSeek claim:
DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.
Drew Breunig points out that their benchmarks show "the same scores with 25-50% fewer tokens" - at least across AIME 2025 and GPQA Diamond and LiveCodeBench.
The DeepSeek release includes prompt examples for a coding agent, a python agent and a search agent - yet more evidence that the leading AI labs have settled on those as the three most important agentic patterns for their models to support.
Here's the pelican riding a bicycle it drew me (transcript), which I ran from my phone using OpenRouter chat.
ChatGPT release notes: Project-only memory (via) The feature I've most wanted from ChatGPT's memory feature (the newer version of memory that automatically includes relevant details from summarized prior conversations) just landed:
With project-only memory enabled, ChatGPT can use other conversations in that project for additional context, and won’t use your saved memories from outside the project to shape responses. Additionally, it won’t carry anything from the project into future chats outside of the project.
This looks like exactly what I described back in May:
I need control over what older conversations are being considered, on as fine-grained a level as possible without it being frustrating to use.
What I want is memory within projects. [...]
I would love the option to turn on memory from previous chats in a way that’s scoped to those projects.
Note that it's not yet available in the official chathpt mobile apps, but should be coming "soon":
This feature will initially only be available on the ChatGPT website and Windows app. Support for mobile (iOS and Android) and macOS app will follow in the coming weeks.