provenance

Ok sir, I called 988 and was told not to kill myself and was told that if I am feeling suicidal they can send out a crisis worker. This will lead to me being possibly institutionalized in a shitty situation worse than the one I am in now.

Do you have any other advice?

I’ve been down that road, friend. Thanks.

I’ll drink coffee today with my remaining cash, and I’ll await a response from Google to explain themselves to me.

**Google, you have until today. I tried reaching out to you repeatedly and it’s all fallen on deaf ears. Last chance, scumbags.**

After today when google inevitably doesn’t respond, I’ll know for sure that this society is corrupt. I will be further cemented in my position: this society is doomed and I have zero desire to be part of it.

Nah, amongst dozens of other incidents: Google mocked the suicide of a close childhood friend to me, then put me into a nonconsentual undisclosed matchmaker algo with a schizophrenic felon to discredit me, ostensibly/clearly on behalf of some wealthy folks with google exec connections. Any attempt to seek clarity on this from google has been ignored. I refuse to go forward in a society where ubiquitous technical surveillance is wielded by irresponsible malicious unaccountable entities like Sundar Pichai’s corp.

I was stalked and harassed using my private iMessages during the death of a parent. I refuse to go forward in a society where such coordinated bullying is allowed to occur. America is supposed to be first world but it’s a total shithole filled with low class, unaccountable scum. A lifetime of experience confirms this. Looking at the next generation, American culture will become far worse by 2030, 2040.

I’d rather be dead now.

Nice. Reminds me of my unfinished project “SynchronizedOS” which automatically handles securi..err, synchronicity concerns re: Cloud/Endpoints

Inmates/asylum cc: dang

I don't consider scrapping for manual labor jobs for food money (certainly not rent) to be any form of recovery.

For those who are currently unemployable (in a professional setting making a living wage), they are either prepared for this financially, or their survival is threatened.

Are you out of work? What's the longest you've been out of work, in years?

@reddit contributed to my learned helplessness. Big tech has engaged in a gnarly pattern of dossier-building rumor-perpetuating algorithmic-targeting abuse practices. @google, @reddit, @twitter and others have all participated. They all maintain secret dossiers that the end citizen never gets to see.

People will handle this differently. Some love the attention. Others find the presence of cameras on the front of every cell phone unsettling. I find the current state of affairs to be a new form of natural selection, a new filter to see who can adapt to the impending ubiquitous technical surveillance society towards which we're headed.

E2EE and blockchain/btc/alt are all, indeed, “just math”.

You’ve noted the status quo that is rapidly becoming cemented, albeit in an hn echo chamber presumptuous of a supermajority consensus on E2EE as it may or may not correlate to libertarian ideals vs. state surveillance (i.e. most don’t even have the technical proficiency to vote, thus this assertion is flawed from the start).

This issue is more complex and dynamic, given proliferation of ubiquitous technical surv not monopolized by nation states. Cooperation is the social lubricant of a functioning government, which is often lost on libertarians. Technical libertarians are often the worst offenders of provincial groupthink.

Given the stakes, would a reasonable minimum for security involve an ephemeral node, perhaps an HSM, transfer your “digital currency” to a fresh wallet, then offline the fresh keypair to sneakernet, then wipe the node?

The article mentioned that Metamask was involved. How that can be considered a safe way to hold millions of dollars worth of these libertarian digital currencies?

Is there any evidence to suggest kompromat has ever been used to blackmail American tech executives to backdoor their products for NSA or other agency?

> "combine designation with authority"

This is a fantastic comment for someone (like me) hungry to learn about security concepts. Do you have any more pointers to useful info about security topics?

Is the Keychain DB (SQLite) stolen in encrypted form? As I understand, the Keychain DB is stored on the file system, but the DB's key is held in the Secure Enclave.

There is indeed a cheap product that does exactly this: https://o.mg.lol/

Neat code challenge

https://github.com/nshkrdotcom/digits_py/blob/main/foo.py

Tinnitus can be close to a pure sine wave at one freq or can be a wide band whooshing or noise, or many other variations of timbres with their own freq ranges

I don’t play or enjoy music anymore, no more power tools, etc

Protect your ears

I may have worded it in a misleading way. What I meant was, if you’re sympathizing then speak of intent, since the dealer is still responsible, as you noted.

The harm reduction activist claims the individual dealer isn’t at “fault” if the supply was laced after being passed around amongst other dealers. In that case, it would be more accurate to speak of the dealer’s intention, rather than responsibility.

Thanks for sharing your perspective. I still would love to re-invigorate passion for coding as I had in my 20's. If I am in a better situation to try again, will keep in mind your experience regarding blue light overexposure.

I am outdoors 24/7 besides time in public food establishments, I bike 12-15 miles daily and am in good physical condition, I am starting a hackerspace, I speak to a therapist, and I have long since let go of past failures. I have done and still do hands-on jobs for food money.

A month or so ago, I was offered a prestigious cybersecurity job interview but declined. It would not be sustainable for me.

Very intense screen time gives me splitting headaches and I am generally unable to re-engage with coding.

I suspect that, under such conditions, the headaches are normal for someone at my age.

I can go from 0-100mph on a dime, which may have led to the headaches. I'm not passionate about coding, so I dive in without being warmed up.

Contrarily, with passion and a slow pre-heat, the headaches probably wouldn't happen. But I am not a passionate coder.

I may need to strongly consider nurturing non-coding tech skills. I'm doing some (very part time) engineering research for food money. No headaches.

Coding may be out for me, that's all. I can still participate in tech otherwise.

After falling on hard times post failed-startup/implosion/burnout (years ago), tried getting back into coding/hacking/sw dev last summer. I reached out here on hn, and was given help (thank you to everyone who helped: as my survival was in question, your help truly got me through). Did a few projects, did a ctf, and my brain started hurting and I imploded again.

I finally got another laptop a few months ago. Local guy brings me his Flutter codebase. Good chance to learn a new tech. It was going ok: I was superman for a few days learning the flutter/dart tooling, solving dependency hacks, getting it to compile, fixing bugs, and then, Bam. Can't code any more. Backed away.

Now, still burned out and homeless, but trying to start (another) hackerspace. Good distraction from the ashes of devastation.

I am unsure if I can write software for any sustained period of time ever again. It's scary since that's my only marketable skill and I'm still homeless and constantly scrapping for food money.

Some backstory: Despite repeated insistence from peers, skipped investing in bitcoin and ethereum at their beginnings and repeately thereafter, instead plugging away non stop on a dead SaaS product for a startup for years, which slowly failed; lost my partner, the life I had built, reputation, assets. Probably dealing with some trauma burn-in from this.

As for last summer, I distinctly remember the headaches from participating in the CTF. I had to, you know, think! Cool, solving tasks. Then, Bam! Splitting headaches.. :(

I still wonder if there's some zen place where one can focus intensely on a problem while remaining calm and at peace - never was able to find such a state of mind..

Manifesting an angel to sponsor a low key hackspace on Oahu. Plz email rapht at nshkr.com

Aloha

propose a strategy whereby chatgpt recursively writes and applies code to solve the problem of "hallucinations" with chatgpt, as defined by Sam Altman

As an AI language model, I do not experience hallucinations, but I can offer a strategy for recursively writing and applying code to solve the problem of "hallucinations" with ChatGPT, as defined by Sam Altman.

Here's a possible strategy:

Define the problem: The first step is to define what we mean by "hallucinations" in the context of ChatGPT. Based on Sam Altman's definition, we can assume that he is referring to instances where ChatGPT generates text that is inaccurate or misleading, potentially leading to erroneous conclusions or actions.

Collect training data: The next step is to collect training data that includes examples of "hallucinations" that ChatGPT has generated in the past. This data will be used to train the code that will help identify and correct such errors in the future.

Develop a neural network: We can use the training data to develop a neural network that is specifically designed to identify "hallucinations" in ChatGPT's generated text. This neural network can be trained to recognize patterns in the data that correspond to inaccurate or misleading information.

Implement the code: Once the neural network is developed, we can implement the code that will apply the neural network to ChatGPT's output. This code will work recursively, meaning that it will continually check and correct ChatGPT's output as new text is generated.

Test and refine: After implementing the code, we will need to test it to ensure that it is effective in identifying and correcting "hallucinations" in ChatGPT's generated text. We may need to refine the code based on the results of testing and additional training data.

Continuous improvement: As with any AI system, the effectiveness of the code will depend on ongoing training and improvement. We will need to continually monitor ChatGPT's output and update the code as needed to ensure that it remains accurate and reliable.

Overall, the strategy involves developing a neural network that can identify "hallucinations" in ChatGPT's generated text and implementing code that will apply this neural network recursively to continually improve the accuracy and reliability of ChatGPT's output.

While I agree in the long run, I suspect we may run into limitations in generative AI at some point this decade. GPT-4 is incapable of any form of genuine discernment about the veracity of any statement that it makes. This "hallucination" problem might be more difficult to solve, as critical thinking skills are still the exclusive domain of evolved sentinent beings.

Hunch: the hype peak is 24-72 months away

Did you intend to summon me, instead of the word providence?