Simon Willison’s Weblog

Newsletter

July 2026

123 posts: 7 entries, 37 links, 17 quotes, 8 notes, 49 beats, 5 newsletters

Friday, 31st July 2026

Release llm-mcp-client 0.1a0

See this blog entry.

31st Jul 2026, 11:03 pm · llm, model-context-protocol

Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)

Visit Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)

Tuesday was Stateless MCP day—the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant change to the MCP spec since it first launched, and has also served to reignite my personal interest in the protocol.

[... 1,316 words]

11:13 pm / projects, ai, datasette, mermaid, generative-ai, llms, llm, anthropic, model-context-protocol

deepseek-ai/DeepSeek-V4-Flash-0731 (via) The latest release in DeepSeek's V4 family, "with substantially enhanced agentic capabilities". It's 304 billion parameters - 167GB on Hugging Face - but it appears to punch well above its weight.

Artificial Analysis rank it ahead of MiniMax M3 - a 428B model. It's $0.14/million input and $0.27/million output pricing means this may currently be the best value-per-intelligence model out there. It's looking very good on the Intelligence Index vs. Cost per Intelligence Index Task chart:

Scatter plot from Artificial Analysis titled with axes "Artificial Analysis Intelligence Index" (20 to 65) and "Cost per Task (USD, Log Scale)" ($0.02 to $3), with a green "Most attractive quadrant" box in the upper left and a dotted "Pareto line". DeepSeek V4 Flash 0731 (max) is highlighted in dark blue at roughly $0.028 and an intelligence score of 50, sitting alone at the far left edge of the green quadrant where the Pareto line jumps sharply upward. Models of similar or lower intelligence like MiniMax-M3, Kimi K3 (low), GLM-5.1 and Kimi K2.6 cost ten times more, and the models that beat it (Grok 4.5, Gemini 3.6 Flash, GLM-5.2, Kimi K3, Claude Opus 5, Claude Fable 5, GPT-5.6 Sol) all sit far to the right at $0.4 to $3 per task.

I got a disappointing pelican from it using the default reasoning level via OpenRouter:

Flat vector illustration of a white pelican with a long neck and large orange beak pouch, hovering above a mangled blue and orange bicycle on a dark grey road with white dashed lane markings. The bike is drawn incorrectly: the wheels are just orange arcs with no rims or spokes, the frame tubes float apart and the handlebars connect to nothing. The background is pale blue with a yellow sun in the upper left, white clouds, and grey speed lines on the left suggesting motion.

But when I bumped reasoning level up to high I got something much better:

llm -m openrouter/deepseek/deepseek-v4-flash-0731 -t pelican -o reasoning_effort high

Flat vector illustration of a white pelican riding a bicycle to the right against a pink background with a lighter pink circle behind it. The pelican grips the handlebars with its wings and one orange foot rests on the pedal, and a small blue fish is visible tucked in the corner of its large orange beak pouch. The bike has a red, blue and orange frame with dark tires, and grey speed lines trail behind to suggest motion.

# 11:59 pm / ai, generative-ai, llms, pelican-riding-a-bicycle, deepseek, llm-release, openrouter, ai-in-china, artificial-analysis

2026 » July

MTWTFSS
  12345
6789101112
13141516171819
20212223242526
2728293031