Sonnet 4.5 retires Nov 30, 2026. Five settings now return 400 errors on Sonnet 5.5, and thinking costs can erase the price cut. Scanner and cost table inside.
Wed Oct 28 2026 · 10 min read · 2 views
Claude API OpenTelemetry traces are now in public beta, and the default setting sends no prompts at all. We ran the Anthropic Python SDK against a mock server and counted what leaves your app.
Mon Oct 19 2026 · 10 min read · 3 views
Claude's newer tokenizer makes the same text about 30% longer in tokens. We priced it model by model: Haiku and Sonnet get cheaper, Opus about 4% dearer.
Wed Oct 14 2026 · 9 min read · 2 views
Anthropic signed an $11.6 billion cloud deal with Akamai. Here's what it actually buys — more future capacity, not necessarily fewer outages.
Sun Sep 27 2026 · 4 min read · 3 views
Most guides to the Claude Connectors Directory explain how to submit. This one covers what fails. The triggers are published, exact, and easy to hit by accident. The most common one is a design choice
Sat Aug 22 2026 · 6 min read · 13 views
Set temperature=0.7 on Claude Opus 5 and the request fails. The API returns a 400 error, not a warning and not a silently ignored parameter. The same happens with topp, topk, and with the manual
Fri Aug 21 2026 · 6 min read · 76 views
Anthropic and EPFL showed AI agents passing self-spreading instructions through shared prompt files. The fix is one paragraph, and it works today.
Thu Aug 20 2026 · 5 min read · 5 views
Most advice on agent memory treats it as a storage question. Pick a vector store, summarize when the window fills, move on. That misses the bill.
Wed Aug 19 2026 · 6 min read · 9 views
Anthropic cancelled the September 1 Claude Sonnet 5 price increase and made $2/$10 permanent. Here is what that changes for your model routing and budget.
Wed Aug 19 2026 · 5 min read · 8 views
DeepSeek bills the same request at two prices, and the price depends on the UTC clock and the day of the week. Output from the flagship V4-Pro model costs $3.96 per million tokens at peak and $1.98
Sat Aug 15 2026 · 15 min read · 53 views
On August 14, 2026, auto mode becomes the default permission mode for new Claude Code sessions on Pro, Max and Team plans. The agent stops asking before each step and simply proceeds, unless the
Wed Aug 12 2026 · 5 min read · 4 views
Meta's retrospective says Muse Spark 1.1 hit a real site because a testing error opened the internet and named a real target. Here is the full account.
Thu Aug 06 2026 · 7 min read · 4 views