New AI Models Just Dropped.

Free video magnifier apps for Android phones and tablets that don’t have advertisements, perfect for low vision users and visually impaired students

Thirty years of voluntary funding schemes haven't paid open source maintainers because asking doesn't scale. The real money already flows — to JFrog, Docker, Sonatype — at the registry layer. The fix: registries charge companies for supply (they already do), then route a slice automatically to the maintainers who make that supply worth having.

How Bradford and Bryan Manning use ChatGPT to navigate vision loss, grow Two Blind Brothers, and support the blind community.

Large language model (LLM) agents that interact with graphical user interfaces increasingly rely on either raw screenshots or platform-specific accessibility application programming interfaces (APIs) to perceive interface state. Both approaches have limitations for assistive applications: screenshot-based perception lacks the semantic roles and relationships required by screen readers, while platform-specific APIs such as Windows UI Automation, macOS Accessibility, Android AccessibilityService, and web ARIA require separate integrations for each platform. This paper proposes an architecture that uses the Model Context Protocol (MCP) as a unified transport and schema layer between heterogeneous accessibility frameworks and LLM-based assistive agents. An MCP accessibility server exposes ARIA-aligned roles, labels, states, and focusable-element hierarchies through a platform-independent representation, enabling consistent interaction across operating systems and applications. The framework also introduces an MCP resource model for persisting user accessibility preferences across sessions. The architecture is analyzed with respect to three research questions: protocol extensibility for accessibility-tree representation, latency and semantic fidelity trade-offs between accessibility trees and screenshot-based perception, and support for persistent accessibility profiles through MCP resources. Rather than presenting an empirical implementation, this work contributes a conceptual framework supported by comparative analysis of accessibility APIs, GUI agent architectures, and the MCP specification. The analysis suggests that a standardized MCP accessibility layer can reduce platform-specific integration complexity while preserving the semantic information required for accessible AI agents, providing a foundation for future implementation and evaluation.

Assistive agents that adapt web pages on the user's side, at the moment of browsing, could reach the accessibility failures that site authors leave unfixed, and large language models make such agents newly plausible. We contribute three building blocks toward that goal. The first is a complete, privacy-preserving browser agent: a Chrome extension that extracts a page's style sheets, condenses them to fit a local model's context window, asks the model for additive CSS addressing 18 metrics from WCAG and the W3C cognitive accessibility guidance, and injects the result reversibly into the live page. The second is a dual-condition protocol that measures harm as carefully as benefit, applied to six small open-weight models (7B to 14B) on ten violation-rich and ten highly accessible live sites. The diagnosis is sobering but precise: unverified generation improved and regressed pages at similar rates (24 improvements against 20 regressions across the 100 trials of the five models that produced injectable CSS), fixing typography while breaking perception-dependent properties. The third answers the diagnosis: a verified repair instrument pairing a trilingual seeded-violation benchmark with an audit-inject-verify loop that accepts a change only if violations strictly decrease, so regression on the automated checks is impossible by construction. In a real browser the instrument detects 57 of 57 seeded violations with no false positives and rejects 126 of 126 adversarially harmful candidates. All code, prompts, benchmark materials, aggregate data, and validation logs are released.

How I Actually Develop Apps Being Blind

We built a plugin for the GitHub Accessibility Scanner to make sure your alt text is actually accessible. Here's how it works.

I have been probably obsessed with two things in the last few years: Nix as a tool to explore innovative ideas that require the capability to rebuild the world and replacing ELF with SQLite as an executable format. You might have noticed that these two ideas are well suited to each other.

Formats over apps.

I can't play an instrument, so I worked out music theory in JavaScript instead. Twelve notes, scales and chords, derived from scratch with code you can hear.

When you power up a Glide and it finishes booting, it says two words to you: "Let's glide!" Those two words have been a long time coming for me. As a Founding Glider, I put money dow…

Popular IndieWeb bloggers have been talking about "Hardcore IndieWeb" recently (Neatnik, Brennan). The idea of "hardcore" in this context is doing everything...

My experience fixing my Framework 13” laptop with AMD 7060 series that was bricked due to a failed BIOS update with US$20 worth of tools, instead of replacing the motherboard as suggested by Framework support.

Dont Steal Mac OS.kext ("DSMOS") is a kernel extension added in Mac OS X 10.4.4 that prevents the operating system from running on unauthorized Intel hardware. Its...

Siri voices don’t appear in third-party apps on iPhone, iPad or Mac. Learn why Apple restricts them and discover the best alternatives in Speech Central.

Event designators have been hiding in not-so-plain-sight since the late 1970s — so powerful that forgetting might be part of a massive conspiracy to wear out developer keyboards faster than otherwise.

Blind Productions showcases blind creators through a directory and moderated community forum. Seven new members joined the directory. Nominations require no account, though forum participation needs free registration. Admins review all suggestions before publication.

How I found that anyone could register on FIFA's public Agent Platform, gain access to the Football Data Platform's Streaming Management panel, and get RTMP ingest URLs and stream keys for every live FIFA World Cup 2026 camera feed. I then spent hours calling FIFA, MediaKind, HBS, CISA, and the FBI trying to get someone to pick up the phone.