guybedo

here's a few options cited in this thread:

whisper based options:

whisper.cpp works well on Mac and runs locally, though fine-tuning vocabulary is desired

noScribe is a good FOSS option

MacWhisper is a highly effective macOS desktop app that processes local files and remote URLs, exporting to various formats

whisperfile is suitable for batch transcription and can run on an M4 mini with an HTTP API

carelesswhisper.app is a local, whisper.cpp wrapper that offers fast transcription for longer audio, noise profiling, and one-time payment, working well on M1

Faster-Whisper-XXL standalone on Windows offers fantastic accuracy due to vocal extraction preprocessing

VoiceInk is an open-source solution that runs a small local model with optional remote/local LLM enhancements

Vibe is an open-source alternative to SuperWhisper

Cloud options:

OpenAI speech-to-text and AssemblyAI are considered high quality, with AssemblyAI being cheap and having robust SDK support

TurboScribe offers a generous free tier for web-based transcription

Hosting OpenAI Whisper large v3 on Modal.com provides a fast, cheap solution with no rate limits

AssemblyAI's Universal ASR has impressive WER, future textual prompting, and PII redaction capabilities

borgcloud.org offers competitive pricing and fast real-time transcription

GCP's Chirp & chirp2 are used for large-scale meeting minute transcription

Microsoft Word 365 (online) Transcribe is a surprisingly effective out-of-the-box solution for English, offering labeled speakers and timestamps

Uploading audio to YouTube can be a 'cheap hack' for transcription

Full summary here: https://extraakt.com/extraakts/transcription-tools-and-workf...

looks like there isn't much to take away from this, here's a few bullet points:

Apple Intelligence models primarily run on-device, potentially reducing app bundle sizes and the need for trivial API calls.

Apple's new containerization framework is based on virtual machines (VMs) and not a true 'native' kernel-level integration like WSL1.

Spotlight on macOS is widely perceived as slow, unreliable, and in significant need of improvement for basic search functionalities.

iPadOS and macOS are converging in terms of user experience and features (e.g., windowing), but a complete merger is unlikely due to Apple's business model, particularly App Store control and sales strategies.

The new 'Liquid Glass' UI design evokes older aesthetics like Windows Aero and earlier Aqua/skeuomorphism, indicating a shift away from flat design.

Full summary (https://extraakt.com/extraakts/apple-intelligence-macos-ui-o...)

here's the answers by category: https://extraakt.com/extraakts/what-are-you-working-on

That's what I'm working on.

here's the list of alternatives, extracted from this thread:

Instapaper is a good alternative.

Readwise Reader is a strong paid alternative, especially for heavy users and those wanting integration with tools like Obsidian.

Raindrop.io is a useful alternative, including its free tier and permanent copy feature.

Matter is another alternative that has been tried.

Self-hosted options like Wallabag, Linkding, Linkwarden, Karakeep, Omnivore, and Shiori exist.

Obsidian Web Clipper can save articles as markdown locally.

Other less common or custom solutions include Feedly, Histre, Walden Pond (defunct print service), Lighthouse, Full Sort, DoubleMemory (Apple ecosystem), Ulry.app, WordPress plugins, simple text files/spreadsheets, or custom scripts.

(Full summary here: https://extraakt.com/extraakts/mozilla-pocket-shutdown-discu...

There's a lot of comments in this thread, I've added a structured / organized summary here:

https://extraakt.com/extraakts/discussion-on-anthropic-claud...

there's a lot to unpack here, i've added a structured/organized summary here: https://extraakt.com/extraakts/ai-humanity-and-fictional-fut...

fwiw here's a more structured/organized version of this thread: https://extraakt.com/extraakts/void-ai-coding-tool-discussio...

i hope you'll find this little tool helpful, i've been using it a lot since i've built it and i quite enjoy using it.

Any feedback, bug report, feature request is welcome!

oops you're right, it's https://extraakt.com

Hi HN,

I'd like to share Extraakts (https://extraakts.com), a tool I created to automatically format and organize HN discussions.

It processes popular threads to provide:

- summary

- discussion topics/themes

- bullet points

It aims to make dense comment threads more digestible. I hope others will find this useful, any feedback is welcome!

fwiw here's this thread in a more structured format: https://extraakt.com/extraakts/community-reaction-to-qwen3-a...

fwiw a well thought criticisim of the chaotic move by the US: https://x.com/StockSavvyShay/status/1908506134270665110

TLDR: https://extraakt.com/extraakts/llama-4-release-analysis

fwiw i've added a summary of this discussion here (https://extraakt.com/extraakts/gpt-4o-image-generation-discu...) to keep track of the main points

this discussion is getting big so i've built a summary, here's a few bullet points:

- Cloud-dependent features for essential appliance functions are undesirable.

- Modern appliances are becoming less durable and harder to repair compared to older models.

- There are valid concerns about privacy and data security with internet-connected home appliances.

- Consumer Reports and similar review sites are not always reliable and trustworthy.

- Simple, locally controlled appliances are preferable for core home appliance functionalities.

- Some smart features, like remote notifications and control, can be genuinely useful and convenient for users in certain situations.

- Smart features might offer specific advantages in shared living spaces or for optimizing energy consumption.

- Developing local-first software for appliances is perceived by some as complex and expensive compared to cloud-based solutions.

- The market will naturally adjust to consumer preferences regarding smart features over time.

- For some users, the effort of returning a product might outweigh the inconvenience of dealing with cloud-dependent features.

- Not all Bosch dishwashers require cloud connectivity, and some models are still considered high quality.

the summary can be found here: https://extraakt.com/extraakts/dishwasher-app-dependency

fwiw i've added a structured summary of the discussion here: https://extraakt.com/extraakts/frontend-development-churn

LLMs are a huge win in that regard.

I delegate most of my frontend tasks to Claude Code, no need anymore to waste hours understanding why the latest version of framework xyz isn't compatible anymore with library abc.

Also, it feels like there's way more boilerplate code, repetitive tasks in frontend land, once again my buddy Claude Code can generate UI components html and typescript code 100x faster that i can

nice discussion, fwiw i added a structured summary here https://extraakt.com/extraakts/java-24-discussion-features-v...

fwiw i've added a summary of the discussion here: https://extraakt.com/extraakts/67d708bc9844db151612d782

fwiw i like your landing page

So much of this depends on the context, goals and personal situation.

The answer won't be the same for a multi millionaire looking to spend his time working on a cool project or for a low wage worker trying to make it and quit a boring job.

If you already have financial freedom, i guess you should aim for the stars, as in go for something big.

I you're trying to reach financial escape velocity and get rid of your 9 to 5 job, you might want to try small ideas first as it should be easier targets and you probably only need one successful project to be free. Then you can go for the big ideas.

Gemini's output:

Our understanding of reality is fundamentally shaped by the power of stories and narratives.

Humanity constantly seeks to impose order and structure on the world through systems and frameworks.

The inherent human drive to create and innovate defines our art, technology, and design.

We are bound by the complex interplay of connection, conflict, and cooperation in our relationships.

Time's relentless flow drives change, progress, and the unfolding narrative of history.

The vastness of the unknown perpetually challenges and defines the limits of human knowledge.

The search for purpose, values, and meaning is a central and ongoing human endeavor.

Abstract concepts and models are powerful tools for understanding and navigating reality.

All living things are interconnected within a complex web of life and ecological relationships.

The future of humanity presents both boundless potential and significant challenges to overcome.

Although a hammer is a useful tool, it's obviously not that advanced of a tool.

As soon as you have an 'advanced' tool that can automate things or do things for you better/faster/with less efforts, you don't need to learn that skill anymore, why would you ?

It doesn't mean the capacity is lost forever and the skill can't be learned anymore, but it's gonna be less and less frequent at the population level.

Nowadays, how many people can:

- make fire without a match or a lighter ?

- add large numbers or do math operations without a calculator ?

- reach a destination without a gps ?

- learn history dates, lists of cities / states / etc...

In the end, it's a bit similar to how species evolve. When a function isn't needed anymore, the organism tends to evolve without it.

> I can still do integrals by hand

good for you if you can do integrals by hand, i would bet though you're in the small minority of people who can do that.

> AI isn't the ultimate tool, it still can't do basic proofs and it's not doing neither automated proofs using a proof assistant language

I meant AI as in human level AI and above. It will for sure be the ultimate (intellectual) tool that can solve any intellectual task.

> Everytime I see someone say something like this I assume they do pretty insignificant work.

I'm having a hard time following your line of thought, although you might be right and i might be doing insignificant work compared to you.

As technology evolves, humans lose their capacities as their tools get better.

What's the average human's mental calculation capacities compared to our ancestors when the electronic calculator didn't exist ? Who can calculate integrals by hand nowadays ?

AI is the ultimate tool. Who needs to get a phd when your computer can do the work / solve the task better than you would do and in a fraction of the time you'd require.

Sure there's still gonna be a need for specialists but on average most humans are losing their capacities because their tools get better.

I don't get what is "financial terrorism" here:

He's making an offer to buy something at twice the price of the other offer on the table.

I'm not sure it'd be a good deal for Musk but it looks like a good deal for the seller.

I don't think the Agents/LLM become the UI, they are going to be the orchestrators, but a well though UI is always going to be more useful than having to chat/write words so that an agent can help you.

It's gonna be: reusable saas components + ai orchestrator + specialized UI

On a related note, there's probably gonna be an extinction level event in the software industry as there's no software moat anymore.

When every application, every feature, every function can be replicated/reproduced by another company in a matter of minutes / hours using AI tools, you don't have a moat anymore.

yes, UBI is the solution usually proposed but i guess there's a few problems.

First problem i see is UBI is gonna be paid by governments when it's (mega-)corporations making (disproportionate) profits thanks to AI and not employing humans anymore.

Something would need to compensate for this.I guess a new taxes scheme based on the number of AI agents a company would employ ?

At first AI models/systems/agents help employees be more productive.

But i can't imagine a future where this doesn't lead to mass layoffs, or hiring freezes because these systems can replace tens or hundreds of employess, the end result being more and more unemployed people.

Sure there's been the industrial revolution and the argument usually is: some people will lose their jobs but many other jobs will be created. I'm not sure this argument gonna hold this time given the magnitude of the change.

Is there any serious study of the impact of AI on society and employment, and most importantly is there any solution to this problem ?

This is hilarious.

Everybody has evidence OpenAI scraped the internet at a global scale and used terabytes of data it didn't pay for. Newspapers, books, etc...