Flux
Couleur d'accent
Extract PDF text in your browser with LiteParse for the web
IA Programmation

Extract PDF text in your browser with LiteParse for the web

LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, using most of the same libraries that LiteParse uses to run in Node.js. Spatial text parsing Refreshingly, LiteParse doesn't use AI models to do what it does: it's good old-fashioned PDF parsing, falling back to Tesseract OCR (or other pluggable OCR engines) for PDFs that contain images of text…

Simon Willison's Weblog
Introducing Data Exports
Cybersécurité Programmation

Introducing Data Exports

Security teams often need alert data in their own infrastructure, alongside the rest of their security telemetry. We're excited to share that Socket alert data can now flow directly into your own cloud storage. Today we're launching Data Exports, a new integration that automatically writes alert changes from Socket to a bucket you own in AWS S3, Google Cloud Storage, or Azure Blob Storage. Data Exports lets you to choose the format that fits your downstream systems, and decide whether you want…

Socket
A pelican for GPT-5.5 via the semi-official Codex backdoor API
IA Programmation

A pelican for GPT-5.5 via the semi-official Codex backdoor API

GPT-5.5 is out. It's available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I've had some preview access and found it to be a fast, effective and highly capable model. As is usually the case these days, it's hard to put into words what's good about it - I ask it to build things and it builds exactly what I ask for! There's one notable omission from today's release - the API: API deployments require different safeguards and we are working closely with partners and customers on…

Simon Willison's Weblog
★ Generate Apple and Google Wallet passes from Laravel
Programmation Web

★ Generate Apple and Google Wallet passes from Laravel

A mobile pass is that thing in your iPhone's Wallet app. A boarding pass, a concert ticket, a coffee loyalty card, a gym membership. Apple calls them passes. Google calls them objects. Both Wallet apps let you generate them, hand them out, and push live updates to the copy that's already on someone's device. We just released Laravel Mobile Pass, a package that lets you generate those Apple and Google passes from a Laravel app and send updates to already issues passes. Together with the package,…

Freek Van der Herten
Quoting Maggie Appleton
IA Programmation

Quoting Maggie Appleton

[...] if you ever needed another reason to learn in public by digital gardening or podcasting or streaming or whathaveyou, add on that people will assume you’re more competent than you are. This will get you invites to very cool exclusive events filled with high-achieving, interesting people, even though you have no right to be there. A+ side benefit. — Maggie Appleton, Gathering Structures (via) Tags: blogging, maggie-appleton

Simon Willison's Weblog
Bitwarden CLI Compromised in Ongoing Checkmarx Supply Chain Campaign
Cybersécurité Programmation

Bitwarden CLI Compromised in Ongoing Checkmarx Supply Chain Campaign

Socket researchers discovered that the Bitwarden CLI was compromised as part of the ongoing Checkmarx supply chain campaign. The open source password manager serves more than 10 million users and over 50,000 businesses, and ranks among among the top three password managers by enterprise adoption. The affected package version appears to be @bitwarden/cli2026.4.0, and the malicious code was published in bw1.js, a file included in the package contents. The attack appears to have leveraged a…

Socket
Behavioral Credentials: Why Static Authorization Fails Autonomous Agents
IA

Behavioral Credentials: Why Static Authorization Fails Autonomous Agents

Enterprise AI governance still authorizes agents as if they were stable software artifacts.They are not. An enterprise deploys a LangChain-based research agent to analyze market trends and draft internal briefs. During preproduction review, the system behaves within acceptable bounds: It routes queries to approved data sources, expresses uncertainty appropriately in ambiguous cases, and maintains source […]

O'Reilly Radar — AI/ML
Community Corner: The AI Refactor with Kumuda Sreenivasa
Programmation Web

Community Corner: The AI Refactor with Kumuda Sreenivasa

In this episode, Scott talks Kumuda Sreenivasa about her talk on using AI to help with refactoring/replacing legacy system that she’s be presenting at JStek 2026. Links: Our Discord – https://discord.gg/aMTxunVx Buy our shirts – https://store.phparch.com/products/community-corner-podcast-t-shirt Kumuda’s Links: LinkedIn – https://www.linkedin.com/in/kumudas/ Scott’s Links: Website – https://scott.keck-warren.com/ Bluesky – https://bsky.app/profile/scottkeckwarren.bsky.social LinkedIn –…

PHP Architect
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model
IA Programmation

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model Big claims from Qwen about their latest open weight model: Qwen3.6-27B delivers flagship-level agentic coding performance, surpassing the previous-generation open-source flagship Qwen3.5-397B-A17B (397B total / 17B active MoE) across all major coding benchmarks. On Hugging Face Qwen3.5-397B-A17B is 807GB, this new Qwen3.6-27B is 55.6GB. I tried it out with the 16.8GB Unsloth Qwen3.6-27B-GGUF:Q4_K_M quantized version and llama-server using…

Simon Willison's Weblog
Esc