The real product is the agent harnesses, which to be fair can be trained specifically to work with an in-house harness, but not sure it's necessary to own the models, especially if Chinese companies are licensing theirs for fine-tuning like we see with Cursor.

These alternative platforms are like nicotine free cigarettes.

They might garner small communities, which is totally cool and valid, but they will never slay the giants.

I'm hoping they're cooked because they're putting all of their eggs in the AGI basket instead of making useful AI products, and they probably won't figure out AGI.

It might all be moot tho if nobody can buy RAM and we're all pushed to cloud computing (yay Azure...). Then your terminal's OS will be pretty irrelevant.

In the meantime, should the public be worried about MNPs in their bodies?

Given the very limited evidence, Prof Lamoree said she could not say how concerned people should be: “But for sure I take some precautions myself, to be on the safe side. I really try to use less plastic materials, especially when cooking or heating food or drinking from plastic bottles. The other thing I do is ventilate my house.”

“We do have plastics in us – I think that is safe to assume,” said Materić. “But real hard proof on how much is yet to come. There are also very easy things that you can do to hugely reduce intake of MNPs. If you are concerned about water, just filtering through charcoal works.” Experts also advise avoiding food or drink that has been heated in plastic containers.

Do you consume tons of information but wish you retained more of it? Me too. Over the holidays I vibe-coded MasterFlasher, an Android app that turns content into AnkiDroid flashcards without interrupting what you’re doing.

The core insight: the moment you think “I should remember this” is rarely the moment you want to stop and make flashcards. MasterFlasher lets you silently share content from any app to an inbox, then batch-process it into cards later.

How it works:

Share from any app → content saves silently to a local inbox (no UI interruption)

URLs: in-app browser extracts article text via Readability.js

PDFs: text extracted on demand via pdf.js

Flashcard generation uses a multi-step Gemini pipeline: fact extraction → scoring → card generation

Review/edit cards, then push directly to AnkiDroid

Design choices:

Capacitor + Ionic + React, with Java plugins for the in-app browser and Room storage

BYOK: you provide your own Gemini API key (no server or proxy)

API keys stored on-device using Android KeyStore

Prompts are user-editable if you want to tweak output

Everything is local except the Gemini calls

For context: I’m not a software engineer. This is a hobby project to solve my own problem. I’ve since learned that LLM-generated flashcards aren’t an original idea, but I wanted something that fit my workflow: offline, share silently, process later, push straight to AnkiDroid. It also just seemed fun to build.

Free and open source. APK and source on GitHub: https://github.com/mortsnort/MasterFlasher

I don't have plans to monetize or go much further with this, but I'd welcome ideas for making it more useful for my own flashcard learning. Thanks for checking it out!

Comments URL: https://news.ycombinator.com/item?id=46459623

Points: 3

# Comments: 0