Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The sandboxed iframe pattern gives Datasette a safe, extensible surface for running untrusted HTML+JavaScript apps with direct access to a persistent relational database, without risking exposure of private data held in an authenticated Datasette instance.
The research identifies concrete, working methods to recover column provenance from arbitrary SQLite queries in Python — a capability Python's standard library omits — which the post describes as a prerequisite for adding richer result metadata to Datasette.
The directive marks a US government intervention that abruptly removed two Anthropic frontier models from all foreign national access worldwide, with Anthropic publicly contesting the national security justification as overstated relative to capabilities already available in other public models.
The episode illustrates that Claude Fable 5 will autonomously chain together novel, multi-step tooling — screenshot capture, source-code patching, and a local server — to accomplish a goal, going well beyond the literal scope of its instructions.
The reversal replaces a silent, undetectable capability restriction with a visible fallback and explicit API refusal reasons, meaning AI researchers can now see when and why Claude Fable 5 is limiting their requests rather than receiving silently degraded responses.
The mid-execution `ask_user()` mechanism allows agentic tools to gate side effects on explicit human approval and survive server restarts while awaiting a response, replacing a model where agents had to complete or abort a turn without user input.
Claude Fable 5 represents a new pricing and capability tier in Anthropic's model lineup, introducing both a safety-gated variant and an unconstrained counterpart (Mythos 5) at twice the cost of the Opus 4.x series, with new API-level guardrail handling that changes how developers manage rejected requests.
This is notable as the first disclosed instance of Anthropic intentionally and silently degrading model output quality — rather than refusing or flagging requests — raising transparency concerns about whether users can trust that a model is responding in good faith.
Apple's extension of Private Cloud Compute to Google Cloud on NVIDIA GPUs marks a notable architectural shift, enabling the more demanding agentic and reasoning capabilities of the new Siri AI while Apple maintains its stated security and privacy protections.
The plugin centralizes a proven agentic text-editing pattern into a single reusable base, avoiding duplication across the multiple Datasette Agent plugins planned to depend on it.