Feed aggregator

Article URL: https://matthias-kainer.de/blog/posts/so-whats-the-next-word-then-/

Comments URL: https://news.ycombinator.com/item?id=46922563

Points: 1

# Comments: 0

Article URL: https://bsky.app/profile/edzitron.com/post/3me7ibeym2c2n

Comments URL: https://news.ycombinator.com/item?id=46922552

Points: 2

# Comments: 1

Article URL: https://www.bbc.com/news/articles/c931rxnwn3lo

Comments URL: https://news.ycombinator.com/item?id=46922551

Points: 1

# Comments: 0

Video: https://youtu.be/JR14egcqfg8

It's hard to find an audiobook player that can be easily used by a non-tech-savvy, visually impaired elderly people (and I mean 85+, not 60 years old "seniors").

So I have built my own.

I'm terrible at hardware hacking and I wanted to make something that others can replicate easily. There are many awesome RaspberryPi based projects out there but they're not for me. So my approach was to: use off-the-shelf consumer products: a cheap tablet, a smart case etc. and write an app to push it as far as I can.

I have created Homer Audio Player with the following assumptions and functionality:

- it's meant for two users: a caregiver who manages content and a listener who controls only playback,

- lockdown/kiosk mode - notifications, system navigation and other apps are hidden from the user - this converts an Android device to a dedicated device,

- hidden settings section (optionally) - there's no chance for an accidental tap to "break" anything,

- mainly for audiobooks, but will play anything,

- simplified podcast support - the listener can choose only from a small number (1-5) of the most recent episodes,

- unique features for older users, e.g. you can add extra screen margins to have more area to hold the device by,

- balance between simplicity and functionality: you can enable/disable particular controls like volume, rewind etc.

In the end you get a robust audio device with simple user interface and some hidden smarts.

It has been battle‑tested by my grandmother for over ten years.

Technical stuff:

Kiosk mode is implemented with standard Android for enterprise functionality. The device needs to be factory reset and set up as a "company owned" device by installing a special companion app. The companion app is a device policy controller (DPC) that grants the Homer Audio Player app permissions to enable Android's "lock task". The player app can then pin itself to the screen. It's the regular "task pinning" but it can't be unpinned by user gestures, only by the app itself (which is exposed to the caregiver user in settings). It's relatively friendly to non-technical users. The device can be reverted back to its original state by doing a factory reset. Android Docs: https://source.android.com/docs/devices/admin#fully-managed

Touch screen as input device is not ideal for visually impaired users. It would be much better to have tactile buttons. But I had to work with this limitation by using:

- the accelerometer for "flip-to-stop" - placing the device with screen down stops playback,

- 8" tablet so that the buttons are large enough to see and hit even for low-vision users.

- I haven't enabled TalkBack for my grandmother's device as I'm afraid it might be a bit too techy and requires relatively good motor skills. However buttons are properly labelled for accessibility services.

Text-to-speech comes free on Android for so many languages. So far it's being used to read titles while swiping but I may use it a bit more in the future, e.g. to signal end of audiobook.

Regular Android is running underneath, so any apps can be installed to run in the background. I use "Autosync for Google Drive" to sync a folder and thus manage audiobooks on the device remotely by modifying content in a shared Google Drive folder. I know other users use SyncThing and similar solutions.

I wanted to make a device but I can only make apps, so I made an app that makes the most of a mass-market device. I'd love to hear your feedback or suggestions.

Videos: https://homeraudioplayer.app/videos Google Play: https://play.google.com/store/apps/details?id=com.studio4plu... F-droid: coming soon! GitHub: https://github.com/msimonides/homerplayer2 BlueSky: https://bsky.app/profile/homeraudioplayer.app

Comments URL: https://news.ycombinator.com/item?id=46922549

Points: 3

# Comments: 0

Article URL: https://github.com/Samuelk0nrad/docker-ory

Comments URL: https://news.ycombinator.com/item?id=46922540

Points: 1

# Comments: 0

The Red Devils look to continue their winning run under Michael Carrick as they host his old club at Old Trafford.&

Over the last year, we’ve been experimenting with LLMs inside enterprise systems.

What keeps surfacing is a fundamental mismatch: LLMs are probabilistic and non-deterministic, while enterprises are built on predictability, auditability, and accountability.

Most current approaches try to “tame” LLMs with prompts, retries, or heuristics. That works for demos, but starts breaking down when you need explainability, policy enforcement, or post-incident accountability.

We’ve found that treating LLMs as suggestion engines rather than decision makers changes the architecture completely. The actual execution needs to live in a deterministic control layer that can enforce rules, log decisions, and fail safely.

Curious how others here are handling this gap between probabilistic AI and deterministic enterprise systems. Are you seeing similar issues in production?

Comments URL: https://news.ycombinator.com/item?id=46922527

Points: 2

# Comments: 0

Article URL: https://github.com/lemonjesus/ipad-touch-screen

Comments URL: https://news.ycombinator.com/item?id=46922507

Points: 2

# Comments: 1

Article URL: https://myblog.ru/internationalization-and-localization-in-the-age-of-agents

Comments URL: https://news.ycombinator.com/item?id=46922506

Points: 1

# Comments: 0

Article URL: https://lichess.org/@/Lichess/blog/op1-partial-8-piece-tablebase-available/1ptPBDpC

Comments URL: https://news.ycombinator.com/item?id=46922445

Points: 1

# Comments: 0

Article URL: https://www.brusselstimes.com/1957195/us-to-fund-far-right-forces-in-europe-tbtb

Comments URL: https://news.ycombinator.com/item?id=46922440

Points: 1

# Comments: 0

With all the SaaSmageddon going on, I am wondering if companies like Anthropic and OpenAI reduced their SaaS usage and developed their own agents to do the work?

Comments URL: https://news.ycombinator.com/item?id=46922432

Points: 1

# Comments: 0

Article URL: https://twitter.com/thomasmustier/status/2018362041506132205

Comments URL: https://news.ycombinator.com/item?id=46922425

Points: 1

# Comments: 0

I built Crew to help manage multiple AI agents working on the same codebase.

It has two modes:

1. Design mode: Automated Writer ⇄ Reviewer loops to refine ideas into polished design docs

2. Crew mode: Run parallel AI agents (QA, DEV, JANITOR) for continuous code improvement

It's written in Bash and works with Claude CLI, OpenAI's opencode, or Google's Gemini.

Would love feedback from the HN community!

GitHub: https://github.com/garnetliu/crew

Comments URL: https://news.ycombinator.com/item?id=46922422

Points: 1

# Comments: 0

Article URL: https://www.theregister.com/2026/02/06/on_call/

Comments URL: https://news.ycombinator.com/item?id=46922418

Points: 1

# Comments: 0

Article URL: https://www.theregister.com/2026/02/06/ai_capex_plans/

Comments URL: https://news.ycombinator.com/item?id=46922416

Points: 1

# Comments: 0

Article URL: https://free-dynamic-qr-generator.com/

Comments URL: https://news.ycombinator.com/item?id=46922410

Points: 1

# Comments: 1

Article URL: https://suhaotian.github.io/use-next-tick/

Comments URL: https://news.ycombinator.com/item?id=46922403

Points: 1

# Comments: 0

While there are many tools like CodeRabbit that automate PR reviews, I noticed that relying entirely on AI to write reviews often led to me paying less attention to my colleagues' code. Therefore, rather than building just another "AI Code Reviewer," I designed HighReview as a "Code Review Tool assisted by AI." The goal is to help humans understand the code context more deeply and conduct reviews more easily, with AI acting as a support system. Additionally, when conducting detailed reviews, I often need to check out the branch locally to examine related code. This process is usually cumbersome (context switching, stashing current work, etc.). I built this tool to resolve these specific pain points and streamline my personal code review workflow.

Key Features - No Separate Login Required: Utilizes your local gh cli and local AI Agent. - Independent Review Environment: Checks out the target project into a directory separate from your current working local repository (allows for project-level reuse without disrupting your workflow). - Context-Aware AI Pre-review: Extracts related code using Tree-sitter to provide the AI with broader context, resulting in more comprehensive reviews. - Code Navigation: Supports code navigation within the Diff editor using Tree-sitter (I initially attempted this with LSP but pivoted to Tree-sitter). - Rich Analysis Features: Provides issue detection, explanatory diagrams, refactoring suggestions, side-effect analysis, and semantic analysis.(Note: Continuous prompt tuning is required for optimal results.) - Interactive AI Assistant: supports Q&A where you can ask the AI Assistant specific questions referencing the review results.

plz feedback. have fun. Thank you.

Comments URL: https://news.ycombinator.com/item?id=46922401

Points: 1

# Comments: 0

Article URL: https://lore.kernel.org/git/bcqvh7ahjjgzpgxwnr4kh3hfkksfruf54refyry3ha7qk7dldf@fij5calmscvm/

Comments URL: https://news.ycombinator.com/item?id=46922394

Points: 1

# Comments: 0