Flux
datasette-agent 0.3a0
IA Programmation

datasette-agent 0.3a0

Release: datasette-agent 0.3a0 New tool, execute_write_sql, which requests user approval and then writes to a database - taking user permissions into account. #27 I added a mechanism for asking user approval in datasette agent 0.2a0. The new execute_write_sql tool can now prompt the user for all kinds of useful operations. Here's an example where I add some pelican sightings to my pelican_sightings table: The new version also enhances the datasette agent chat terminal mode to support approvals,…

Simon Willison's Weblog
"They screwed us": Personality clashes sent Anthropic's models offline
IA Programmation

"They screwed us": Personality clashes sent Anthropic's models offline

"They screwed us": Personality clashes sent Anthropic's models offline Lots of "source familiar with the administration's thinking" and "source close to Anthropic" in this Axios piece, which is the best collection of behind-the-scenes gossip I've seen about the US government export control Mythos/Fable story so far. Logan Graham (I lead the Frontier Red Team at Anthropic), Dave Orr (Head of Safeguards, previously a Director of Engineering at Google DeepMind), and blog favorite…

Simon Willison's Weblog
Socket for Linear Is Now Available
Cybersécurité Programmation

Socket for Linear Is Now Available

When Socket flags a malicious package or a vulnerable dependency, some fixes are quick: bump a version, drop a package, patch and move on. Plenty of others need to be tracked, assigned to the right person, and prioritized against everything else a team is working on. That kind of work lives in an issue tracker. Linear has earned a loyal following among engineering teams, prized for its speed and the clarity of its workflow. So today we're excited to announce Socket for Linear, which plugs…

Socket
Why AI hasn’t replaced software engineers, and won’t
IA Programmation

Why AI hasn’t replaced software engineers, and won’t

Why AI hasn’t replaced software engineers, and won’t Arvind Narayanan and Sayash Kappor take on the question of AI job losses through the lens of a profession that is uniquely suited to AI disruption - software engineering. In this essay, we argue that there is enough evidence to reject the narrative that once AI capabilities reach a certain threshold, it will cause mass layoffs. Given that this is true even in a sector with very few regulatory barriers, most other professions are likely to be…

Simon Willison's Weblog