Flux
Couleur d'accent
Toutes les catégories

IA

2461 articles

Beyond the Semantic Layer: Building a Context Layer for the Agentic Era
Programmation IA

Beyond the Semantic Layer: Building a Context Layer for the Agentic Era

Writing SQL was never the hard part. Making it accurate and trustworthy against your warehouse always was. Point an AI agent like Claude or Codex at your data stack and ask a real analytics question, and the answer is usually mediocre: the agent can scrape some context from your git repos or whatever metadata it can find, but it doesn’t know your joins, your metric definitions, or the business rules that give a number its actual meaning.

SSP Data Engineering Blog
Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude
IA Programmation

Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude

Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude Big scoop for Maxwell Zeff at Wired: “We’re changing Fable 5’s safeguards for frontier LLM development to make them visible.” Anthropic said in a statement to WIRED. “We made the wrong tradeoff and we apologize for not getting the balance right.” There's been a huge outcry about Anthropic's policy, tucked away in their system card, that Claude Fable/Mythos would identify "requests targeting frontier LLM…

Simon Willison's Weblog
datasette-agent 0.2a0
IA Programmation

datasette-agent 0.2a0

Release: datasette-agent 0.2a0 Highlights from the release notes: Tools can now ask the user questions mid-execution. Tools that declare a context parameter receive a ToolContext object, and await context.ask_user(...) can ask a yes/no, multiple-choice (options=[...]) or free-text (free_text=True) question. While a question is unanswered the agent turn suspends: the question renders as a form in the chat UI and persists to the internal database, so suspended conversations survive a server…

Simon Willison's Weblog
DiffusionGemma
IA Programmation

DiffusionGemma

DiffusionGemma Last May Google briefly released an experimental Gemini Diffusion model. I tried the preview at the time and recorded it running at 857 tokens/second. It was an exciting model, but Google made no further announcements about it. That research has returned in the best possible way: as a new open weight (Apache 2 licensed) Gemma model, google/diffusiongemma-26B-A4B-it. NVIDIA are currently hosting the model for free on their NIM cloud API. I used that API to generate this pelican,…

Simon Willison's Weblog
Quoting Jeremy Howard
IA Programmation

Quoting Jeremy Howard

Easy solution to slow down recursive AI self improvement: The lab with the top-ranked model must agree THEY must not use it for working on frontier AI But everyone else should have access to it. By definition, this means the frontier doesn't advance. It also has the critical benefit of avoiding a dangerous power imbalance. Anthropic has chosen the opposite of the safe path: they are allowing themselves, the current top lab, to use their top model for frontier AI research. They've said they'll…

Simon Willison's Weblog
The PM’s Playbook for Shipping AI Features That Actually Work in Production
IA

The PM’s Playbook for Shipping AI Features That Actually Work in Production

The demo to production Death Valley If you’ve worked on an AI feature, you know the feeling. You start building something that you are excited about, set launch timelines. The model spits out a perfect response, the prototype works magically, and everybody in the room is mentally calculating how big this product will be when […]

O'Reilly Radar — AI/ML
If Claude Fable stops helping you, you'll never know
IA Programmation

If Claude Fable stops helping you, you'll never know

If Claude Fable stops helping you, you'll never know Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system card for Fable 5 and Mythos 5. Here's a longer excerpt, highlights mine: In light of the ability of recent models to accelerate their own development, we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training…

Simon Willison's Weblog
Initial impressions of Claude Fable 5
IA Programmation

Initial impressions of Claude Fable 5

I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow, expensive and has been quite happily churning through everything I've thrown at it so far. As is frequently the case with current frontier models the challenge is finding tasks that it can't do. First, let's review the key characteristics. Anthropic claim that Claude Fable 5 offers the same…

Simon Willison's Weblog
Setting a custom price for a model in AgentsView
IA Programmation

Setting a custom price for a model in AgentsView

TIL: Setting a custom price for a model in AgentsView I've been really enjoying AgentsView by Wes McKinney as a tool for exploring my token usage across different coding agents running on my laptop. Claude Fable 5 came out today and wasn't yet included in the pricing database AgentsView uses. I used Fable to reverse-engineer AgentsView and figured out this recipe for setting custom prices. Here's my Claude Fable 5 usage for today so far, plotted by AgentsView as a treemap across my different…

Simon Willison's Weblog
Quoting Andrej Karpathy
IA Programmation

Quoting Andrej Karpathy

I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). — Andrej…

Simon Willison's Weblog
Siri AI at WWDC 2026
IA Programmation

Siri AI at WWDC 2026

Given how badly burned anyone who took Apple's 2024 WWDC Apple Intelligence announcements at face value was, I'm holding to a strict "I'll believe it when I see it" policy for everything they announced today. The new Siri AI features do at least look feasible with today's technology, especially since Apple are licensing a custom Gemini-derived model that they can run on their own Private Cloud Compute. It sounds like they'll be taking advantage of vision LLMs to extract information from the…

Simon Willison's Weblog
Esc