Datasette wires fixtures, Ronacher cuts bugs to 4 lines, Claude ports a 1983 PDF
Every URL the pipeline pulled into ranking for this issue — primary sources plus the supporting and contradicting findings each Researcher returned. Inline citations in the issue point back here.
Sources
datasette 1.0a30 simonwillison.net
Release: datasette 1.0a30 The big new feature in this alpha is a new customizable “Jump to…” menu, described in detail in The extensible “Jump to” menu in Datasette 1.0a30 on the Datasette blog. You can try it out by hitting / on latest.datasette.io - it looks like this: The new jump_items_sql() plugin hook allows plugins to add their own items to the set that’s searched by the plugin. Tags: projects , datasette , annotated-release-notes
datasette-agent 0.1a4 simonwillison.net
Release: datasette-agent 0.1a4 Taking advantage of the new makeJumpSections() JavaScript plugin hook added in Datasette 1.0a30 , datasette-agent now presents this “Start a new agent chat” interface as part of the Jump to menu, any time you hit / : You can try this out by signing into agent.datasette.io using your GitHub account. Tags: datasette , datasette-agent
datasette-fixtures 0.1a0 simonwillison.net
Release: datasette-fixtures 0.1a0 One of the smaller features in Datasette 1.0a30 is this: New documented datasette.fixtures.populate_fixture_database(conn) helper for creating the fixture database tables used by Datasette’s own tests, intended for plugin test suites. This new plugin takes advantage of that API. You can try it out using uvx without even installing Datasette like this: uvx —prerelease=allow \ —with datasette-fixtures datasette \ —get /fixtures/roadside_attractions.json Which…
Quoting Armin Ronacher simonwillison.net
The most frustrating failure mode right now is that people submit issues that are not in their own voice. They contain an observed problem somewhere, but it has been thrown into a clanker and the clanker reworded it and made a huge mess of it. Typically, it was prompted so badly that the conclusions produced are more often than not inaccurate but always full of confidence. The result is complete guesswork on root causes, fake-minimal repros, suggested implementation strategies, analogies to adj…
Mad House — Usborne Creepy Computer Games simonwillison.net
Tool: Mad House — Usborne Creepy Computer Games Via Hacker News I learned that UK publisher Usborne published free PDFs of their 1980s Computer Books , some of which I remember working through on my Commodore 64 as a child. These were so great! Beautifully illustrated books with fun projects made up of code you could type into your own machine. I remember playing “Mad House” typed in from the 1983 book “Creepy Computer Games”, so I fed that PDF into Claude and had it build an interactive versio…
References
Simon Willison Substack — ‘Datasette Agent, an AI assistant’ simonw.substack.com
The agent successfully queried a blog database to find his most recent ‘pelican sighting’… the ‘export Markdown’ feature was particularly highlighted as a way to maintain a reproducible audit trail of the agent’s SQL logic and results.
datasette.io blog — Datasette Agent announcement datasette.io
Datasette Agent supports a wide array of backends, including OpenAI’s GPT-5.5 and Google’s Gemini 3.5 Flash… ‘plugin-first’ architecture… datasette-agent-charts and datasette-agent-sprites plugins as evidence that the system is a viable platform for ‘vibe coding’.
PopAI Explorer — Datasette Agent coverage popaiexplorer.com
Because datasette-agent can execute SQL and potentially run code via plugins like datasette-agent-sprites (which uses a Fly Sprites sandbox), it resides in a high-risk category for prompt injection… the ‘lethal trifecta’ of agent security: access to private data, exposure to untrusted content, and the ability to communicate externally.
AIMultiple — Text-to-SQL benchmarks 2026 aimultiple.com
Top-tier models (Claude Sonnet 4.5 and GPT-5) achieve 90-95% accuracy on simple schemas… a significant drop to 60-70% on complex enterprise datasets. Common failure modes include ‘faulty joins’ and ‘hallucinated column names’.
Datasette docs — 1.0a30 changelog docs.datasette.io
Replaced traditional token-based CSRF protection with the modern Sec-Fetch-Site header approach… inspired by Go 1.25 and research by Filippo Valsorda… eliminates the need for hidden tokens in HTML templates. Also introduced RenameTableEvent so plugins like datasette-comments stay synchronized when tables are renamed.
Datasette latest docs — jump_items_sql hook docs.datasette.io
Implementations typically verify if the current ‘actor’ has the execute-sql permission before running the query to populate the menu… designed to respect the underlying SQLite read-only constraints, ensuring that menu-generation queries cannot be used for unauthorized data modification.
The New Stack — curl vs HackerOne thenewstack.io
submissions had spiked to eight times the historical average, while the valid-report rate plummeted from 15% to less than 5%
Rust moderation team spam policy (GitHub) github.com
verbose, LLM-generated messages [are treated] as a form of spam because they force reviewers to act as ‘unpaid QA’ for hallucinations
ZeroPath blog — 170 valid bugs in curl zeropath.com
curl received nearly 170 verified bug fixes from AI tools in a single month
Simon Willison — ‘Slop is the new name for unwanted AI-generated content’ (May 2024) simonwillison.net
slop is AI-generated content that is shared without human oversight or regard for the recipient’s time; ‘don’t publish slop’ is a baseline for AI ethics
OpenSourceForU — Linux Foundation AI defense initiative opensourceforu.com
Linux Foundation launched a $12.5 million initiative to fund ‘AI defense’ tools designed to help maintainers automate the triage of incoming reports
Armin Ronacher — ‘Pi OSS’ (lucumr.pocoo.org) lucumr.pocoo.org
the issue tracker is increasingly serving as a prompt input for AI agents… generation is cheap but review is prohibitively expensive
Usborne Publishing — Computer and Coding Books usborne.com
Usborne Publishing has released the majority of its 1980s computing catalogue as free PDFs and explicitly authorises readers to ‘adapt any of the programs in these books to modern computer languages’ and share those adaptations freely online.
filscentia/spacegames (GitHub) github.com
Reinterprets the Usborne Computer Spacegames book into Node.js and Python, designed to run from the command line — part of a small ecosystem of manual, hand-ported preservation projects that predate LLM-assisted recreations.
BoingBoing — ‘Usborne releases free PDFs of its 1980s computer books’ boingboing.net
The books’ heavy use of colourful illustrations and personified robots to explain memory and loops kept readers engaged, a sharp contrast to the ‘stranglehold of markdown’ in modern technical guides.
Simon Willison — ‘Everything I built with Claude Artifacts’ (Substack) simonw.substack.com
Documents over 200 single-file HTML tools built via the Artifacts pattern, including a ‘Claudeception’ technique where artifacts call window.claude.complete() to orchestrate further LLM requests from inside the generated app.
BiggGo — ‘Claude Artifacts User Issues’ biggo.com
Users report ‘limited output context’ truncating code mid-game and ‘versioning glitches’ where the Artifacts UI fails to update or silently deletes large sections during iteration — a known failure mode for longer retro recreations.
Retro Computing Forum — Usborne 1980s computer books thread retrocomputingforum.com
The original listings were architected for portability via a symbol-based system — triangles for VIC-20, squares for BBC Micro — printed next to lines requiring modification, so a single ZX81-base listing could be retyped on Spectrum, Apple II, TRS-80 or Oric.