Hacker Newsnew | past | comments | ask | show | jobs | submit | foltik's commentslogin

“Hey Claude, users are noticing my product is fundamentally broken. Please shuffle some code, increase the confidence label to 99.6%, and spam the HN thread claiming I identified the root cause of a bug. Frame it as a small edge case. Do not under any circumstances empirically validate the supposed fix.”

Snark aside, I still see 9 previous visits from various countries, down from 900+ previously. It does correctly identify me as being in incognito mode, but if I switch to a normal tab I see a completely different set of previous visits.


Why actually try to understand a problem space? Far easier to prompt a turd into existence, polish it up with a cliché marketing page, and collect public validation from your fellow “hackers”

My guess is <5k for a coherent and intentional expert human design. Certainly <10k.

It’s telling that they can’t fix the screen flickering issue, claiming “the problem goes deep.”


Quite an ignorant comment. It’s literally nothing like using a CPU to prop up an uneven table.

It’s precisely the application of quantum physics that enables current prototypes of these IMUs to achieve 1-2 orders of magnitude less position error accumulation vs. state-of-the-art gyroscopes. Think 0.1m/min vs. 10m/min.

Obviously the tube isn’t the holy grail of applications, it’s just a test bed to improve the technology. Think about why GPS is useful. Imagine that, but entirely self contained.


This isn’t just slop — it’s full-on AI psychosis.

On planet earth — population 8.3 billion — were apes that had not been known to live together harmoniously, having previously thought to be hostile to each other.

The average person can get used to arbitrarily terrible UX. See 87% of the workforce that uses sluggish corporate-bloatware-filled windows laptops every day. It’s only those who have experienced and gotten used to something drastically better that will be sensitive to all the shortcomings.

Apple software used to be that elevated experience for the average person.

Given the lack of basic consistency though, it’s evident that there are no leaders at Apple that care about UX enough to thoroughly design and test the whole software experience anymore. Just a bunch of random teams doing whatever.

I wonder why every large company seems to fall off in the same way?


> Mi-malloc is the better choice if you must preload a library, but there are even better choices.

What’s a better choice?


Linking the allocator into your program when you build it, instead of overriding just malloc and free at runtime. Then you can choose between jemalloc, mi-malloc, TCMalloc, or whatever you please, and get better features such as C++ sized delete. Rust makes this easy with for example "use tcmalloc_better::TCMalloc".


It appears to still be wide open:

  curl -X POST \
    "https://wjynmjluabqwqhtdxbtl.supabase.co/storage/v1/object/list/clipboard-images" \
    -H "authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6IndqeW5tamx1YWJxd3FodGR4YnRsIiwicm9sZSI6ImFub24iLCJpYXQiOjE3NDIzODU1MDQsImV4cCI6MjA1Nzk2MTUwNH0.R6pSgPFgHe3ZU9DfKykE98MC1ObYihWdZuhy9v9Y_p0" \
    -H "content-type: application/json" \
    -d '{"prefix": "7b407af2-f30c-4e37-adc7-b7bf48f2661b"}' \
    | jq


There is also an URL-signing oracle that allows any URL to be signed, so it's still possible to enumerate + download all files.

Example: https://wjynmjluabqwqhtdxbtl.supabase.co/storage/v1/object/s...


> Your encryption key is derived from a master key plus your user ID using PBKDF2 (a secure key derivation function). This means even if someone got access to the database, they couldn't decrypt your data without your specific key.

> Your text gets encrypted on our server using your unique key. The encrypted data gets stored in our database

> When you need it on another device, we decrypt it and send it to you

Please stop advertising this as E2EE.

If you encrypt/decrypt the data on the server, you must have the keys. If someone gets access to the server, they can just decrypt everything since the master key is right there. You might as well base64 encode everything and call that encryption.

E2EE is where only the clients have the keys. Data is encrypted before sending to the server, and decrypted after receiving from the server. That's why it's called end-to-end: the server only ever handles encrypted data that it doesn't have the keys to decrypt.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: