{"data":{"id":"42302a70-0521-4ac7-99e8-1996ea090d89","title":"llm-all-models-async 0.1","summary":"The llm-all-models-async 0.1 plugin allows synchronous (blocking) AI models from LLM plugins to work as asynchronous (non-blocking) models by running them in a thread pool (a group of worker threads that handle tasks in parallel). This solves a compatibility problem where Datasette, which only supports async models, couldn't use sync-only plugins like llm-mrchatterbox.","solution":"N/A -- no mitigation discussed in source.","labels":["industry"],"sourceUrl":"https://simonwillison.net/2026/Mar/31/llm-all-models-async/#atom-everything","publishedAt":"2026-03-31T20:52:02.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["Claude","Datasette","LLM"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-03-31T20:52:02.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":null,"aiComponentTargeted":"framework","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}