This one hurts. We will miss you Mr. Dvorak! RIP
HN user
macinjosh
This project is open source and use the excellent SpeechAnalyzer API on macOS.
100% free and local.
I make an iOS app that uses this API heavily for transcribing diverse audio of varying bitrate and recording quality. The audio often contains music, multiple speakers, sound effects. SpeechAnalyzer almost always gets it.
It can struggle with proper nouns but will return something phonetically similar.
My main gripe is that it requires a separate model download per language. I understand the why they did this (to save disk space). But it makes multi-lingual audio hard to transcribe unless you know ahead of time the languages in the audio.
As an app developer the biggest win from using Apple's model is I don't have to bundle it in my app so my app looks much smaller. If a user has many transcription apps each one could have their own model. If Apple's model is used only one copy is needed.
This is a prime example of why programmers are not seriously considered engineers.
The civil engineer who builds a great suspension bridge probably looks down on the one who builds a bridge over a irrigation ditch in a rural county using a big metal pipe covered with dirt.
Much like you may look down on train builders who make the novelty trains for kids parks.
Software engineering happens to be useful everywhere and most stuff in life is low stakes and the economics do not exist to make it perfect.
However, in aerospace, banking, and other high stakes industries software engineering projects are met with the rigor that is called for.
I want a distributed social network on top of email. Emails don’t have to be human readable. A client could be built to pass and share posts among a network via email messages. Add some clever cryptography and you can build trust networks and keep out spam more reliably.
What a coincidence that northern Virginia is spy central.
The longer I participate in the economy the more it starts to feel like the end stages of a game of monopoly. There is nothing left to own unless you already are wealthy and the only way to get ahead is luck.
Opus 4.7 seems smarter not wiser. More knowledge, maybe, but less grit. It often has been asking me to wrap it up or just be happy with current state, instead of working out a problem.
The secret reason they are doing this is because governments want to be able to identify everyone online everywhere it matters at all time. They want to strip anonymity from computing.
Apple and Google can now credibly claim to governments to have nearly ubiquitous computing platforms that they can guarantee do not run any software that is not approved or antithetical to the goals of authorities. This makes the device safe for storing things like government IDs. OSs and Browsers will be required to present these IDs or at first just attest to them.
Before posting online, renting a server, using an app you will have to idenitfy yourself using your phone or similarly locked down PC (i.e. mac).
The introduction is under the guise as always of protecting the children. In reality they are removing your rights to privacy and free speech.
For now I would be happy if it just explored the problem space and identify the choices to be made and filtered down to the non-obvious and/or more opinionated ones. Bundle these together and ask the me all at once and then it is off to the races.
IMHO, LLMs are better at Python and SQL than Haskell because Python and SQL syntax mirrors more aspects of human language. Whereas Haskell syntax reads more like a math equation. These are Large _Language_ Models so naturally intelligence learned from non-code sources transfers better to more human like programming languages. Math equations assume the reader has context not included in the written down part for what the symbols mean.
I disagree. I have a successful software product that I vibe coded using claude code starting last June. It does something novel and useful that wasn't yet offered on the App Store or any app on Android.
I am not going to say what it is because all of the AI haters will immediately flock to leave it bad reviews and overwhelm my support systems with bad faith requests (something that has already happened).
I've been writing software for 25 years, I know what I am doing. Every bug I shipped was my fault either because I didn't test well enough or I did not possess enough platform knowledge to know myself the right way to do things. "Unknown unknowns"
But I have also learned better ways to do things and fixed every bug using AI tools. I don't read the code. I may scan it to gain context and then tweak a single value myself, but beyond that I don't write or read code anymore.
Its not a magical few shot prompt then reap profits machine. I just feel like a solopreneur ditch digger who just got a lease on a new CAT excavator. I can get work done faster I can also do damage faster if I am not careful.
Beyond this concern,
good thing I don't have a TV!
We need something like SETI@home/Folding@home but for crawling and archiving the web or maybe something as simple as a browser extension that can (with permission) archive pages you view.
The irony of an intelligence agency publishing a "fact book" in the first place is thick.
[flagged]
The degradation does not need to be in the inference it can be in how often inference is used.
It is closed source but the algorithms that decide what Claude code does when, could behave differently when the API responses are slower. Maybe it does fewer investigatory greps or performs fewer tasks to get to “an” answer faster and with less load.
[flagged]
Just ten more years! Take my money!
Apple's locked down ecosystem is enabling the rollout of Digital ID which will eventually be required for Internet access and age verification law. This is why Google is locking down their ecosystem now too.
Call me what you want but it is my belief that the reason google is locking down and Apple refuses to budge is that in the near term future our mobile devices will become our identity online and in public.
Apple already offers digital ID in some states. They can do this partly because they can guarantee to the gov’t the ID is genuine because the user cannot modify the system.
Google needs to be able to do the same thing.
Age verification laws for online services will actually require something like a digital ID and Apple and Google want to be the providers.
wild to me these two companies have always been at odds and it is playing out on an even bigger stage now.
Git is already distributed. We don’t need a hub for it. Just stop using GitHub it is a Microsoft product.
Not sure how open source got bamboozled into paying rent to Microsoft of all companies.
The SDK bundles Claude code and uses it for its agentic work. The SDK really only lets you control the UI layer. It als doesn’t yet fully support plan mode.
Seems to me Apple is getting ready to make the black arrow mouse pointer obsolete.
In the next generation or two iPads and MacBooks are going to essentially merge as a product line.
I wouldn't be surprised if Apple abandons classic macOS (w/ Terminal and a filesystem) all together. To continue to support developers all they need is a tweaked Xcode for Apple dev and their version of WSL for everything else. All the parts are already in macOS/iPadOS (native virtualization and containerization).
iMac and Mac Pro are all but dead now too. Mac Mini and Mac Studio will be the only desktop options and will be bought by people who are Millenials and older or ML/AI praciticioners. We may even see a special AI/Local LLM Mac Studio that would be the equivalent of mac pro of the ai era.
Your fingers will need these big round edges to grab. They may let you use a bluetooth mouse but they aren't going to cater their UX to you.
They year of the Linux desktop has come as commercial desktop OS's die.
This is logical end game of having these economic controls at all. Put a steering wheel on it someone will drive it.
A true free market isn’t at whims of any one person.
kudos for not doing yet another chrome clone.
OpenCode has a workaround already: https://github.com/anomalyco/opencode-anthropic-auth/pull/11
We need a startup to make those super realistic face masks easy to make and use. Celebrities could license their faces to make up for movies and tv being AI generated.
You are anonymous too, so…