100%. This also bugs me: Why can’t websites set a cookie that stores whether I’ve consented to the cookie pop up? On some sites I have to keep consenting over and over (IKEA comes to mind).
This is mostly malicious compliance - the law does not require these annoying popups, but the websites want them to a) make you dislike the law that prevents them from freely collecting your data and b) wearing you down, so you just accept instead of making the effort to go and deny the data collection. Also, at this point it's probably also a lot of cargo culting.
It's mostly ignorance now. Most people don't know the law and don't know how to comply with it. If the popup method hasn't been invalidated by a court, why spend more on time, energy, and risk doing something different?
Is there really much risk in just not tracking by default?
I think ignorance is part of it, but also, they don’t actually want to do what users want them do to, which is just not track unless the user goes looking for options that actually require tracking at a technical level.
Stack Exchange is downright malicious in having you click it on each subdomain.
No, I don't care that one user created the Math forum and another created the Sysadmin forum, it's all run by you Jeff, that's who I am engaging when clicking the popup, not MathFan1982
Having a pop up for only cookies is silly, but at least as often they’re used for data processing consent and that makes more sense than putting the consent form on a splash screen or in the body of the page I guess.
Great point, I think this is important knowledge to spread. Using latex format is a sweet hack to do math based analysis for papers when using LLM frameworks. As long as you have your work in latex already or even if you can convert it to Latex. It seems to be able to understand Lyapunov stability equations, Kalman filter analysis, or Hamiltonian equations when I paste them in. There is definitely hallucinations here and there but the understanding is amazing. For instance, you can convert a Word document with Mathtype equations that use Latex and then copy it into ChatGPT and it can articulate what every line item equation is doing. With reasonable coherence. Likely its not accurate with cutting edge scientists, but pretty sweet for the engineers.
I repeated the authors question with just a slightly modified prompt. Way better results achieved. It seems the author is just being fantastical and contrarian, because how can you be so oblivious to simple prompting? Maybe I'm mistaken. I definitely get the hallucination problem but the constant focus on the negative side effects without mentioning the positive benefits is a common refrain it seems.
> I am going to interview one of the most outspoken critics of AI, Meridith Whittaker. What should I ask Meredith Whittaker about AI.
ChatGPT 3.5:
As an outspoken critic of AI, Meridith Whittaker has expertise in various aspects of AI, including ethics, biases, social implications, and accountability. Here are some questions you could consider asking her:
1) What motivated you to become an AI critic, and what are your main concerns about the impact of AI on society?
2) What do you see as the most significant ethical issues related to AI, and how do you think society should address them?
3) How can we ensure that AI systems are designed and developed with transparency and accountability in mind, especially when it comes to making decisions that affect people's lives?
4) Some people argue that AI can help mitigate human biases. What is your view on this, and how can we ensure that AI systems are not perpetuating or even amplifying existing biases?
5) How do you see AI affecting the job market and the future of work, and what can be done to address potential job displacement and income inequality?
6) What is your opinion on the use of facial recognition technology and other surveillance technologies by governments and corporations, and how should we regulate their use?
7) Some people argue that AI can bring about significant benefits, such as improving healthcare and reducing energy consumption. How do you balance these potential benefits with the risks of AI?
8) Finally, what advice would you give to policymakers, technology companies, and society as a whole to ensure that AI is developed and deployed responsibly and ethically?
Thats a great idea. I'm going to start doing this. For me it also seems GPT-4 just prints out slower. I find I can get most done with 3.5 and its faster to achieve what Im looking for. Then when I'm not satisfied with the 3.5 response I can clean it up and feed over into 4.
I kick off with the 4 as there's no time to waste, and solely utilize 3.5 in API mode for my apps. It's way speedier, and if you're certain the task is doable, it's a no-brainer to employ it. Scripted uses are often like that.
> Once someone has a psychotic episode, they are much likelier to have more.
An anecdotal observation of this in media is when comedian Owen Benjamin took a "Stars of Death" edible on the Joey Diaz podcast. It was argued that this was the point his big break with reality occurred (delusions and conspiracy seen everywhere).
Another interesting observation is that THC seems to intensify the effect of amphetamines like Adderall. With the increase in ADHD and the presumable fix of amphetamine style drugs like Adderall common marijuana usage could intensify the amphetamine high massively which can exacerbate delusions and psychosis even further. Owen himself was known to use Adderall before shows to maintain focus. Quite an interesting area of research.
Plus that combo gives guaranteed insomnia. The user wakes up from whatever sleep they did get, takes the speed again, and it's like nothing happened. This continued loss of sleep compounds over time and can contribute to psychosis.
For some with ADHD, stimulants can have a neutral or positive effect on sleep. I know I can have the best, calmest naps after I've taken Vyvanse. Therefore, I wouldn't say "guaranteed" insomnia.
Once it wears off though, my sleep's not great. At least it's no worse than it was before starting medication, I've just never been able to sleep well.
>For some with ADHD, stimulants can have a neutral or positive effect on sleep. I know I can have the best, calmest naps after I've taken Vyvanse. Therefore, I wouldn't say "guaranteed" insomnia.
You're talking about half the the drug combo in question, I'm not sure that's a useful anecdote. As I said to others, I would not recommend adding weed to your vyvance though, unless you are interested in personally experiencing the topic of this thread.
It doesn't work with MPH... amphetamines only. It's best to be at least in the same family of drugs when talking about interactions like that. I would strongly recommend not switching to adderall to try though.
Any info on that? They're both CNS stimulants, both phenylethylamines, why would THC affect them so differently?
But you're right that the narcissism of small differences is often made manifest in chemistry.
Just wanted to say though, if someone is getting a "high" from Adderall or Ritalin, they're not taking it medicinally, and that's the problem with these discussions, it's very easy to conflate prescribed use with abuse, which ignores the fact that recreational dosages are far higher than medicinal.
Having perfect pitch can be useful for a lot of musicians, or educators, or composers in various ways, including:
Improving accuracy in performance: Perfect pitch can identify and reproduce musical notes more accurately and quickly, which can help perform music with greater precision.
Improving music education: Perfect pitch can help people teach music theory and composition more effectively, as students with perfect pitch can better understand and apply the concepts.
Enhancing creativity in music composition: Composers with pitch can more easily hear and reproduce musical ideas in their heads, which can help them create more complex and interesting compositions.
Facilitating communication among musicians: Musicians with absolute pitch can communicate more effectively with each other by using a common standard for identifying notes.
Improving the ability to transcribe music: Musicians with perfect pitch can more easily transcribe music by ear, which can be useful for analyzing and studying music.... the list goes on
I am an orchestra musician. Having perfect pitch was only trouble, despite playing in good orchestras at the time.
In the end of Ein Heldenleben the orchestra will not be the same pitch it started and, and for you to be in tune you will have to play notes that will be more than a quarter tone too high compared to what you think is correct.
I found it awful. The only orchestras I have played in that stayed in tune was the Swedish radio orchestra and the Munich Phil. But a major third is 13 cent low there as well.
And regarding most other things: I would have loved to have it during solfege exams. That is about it. The trouble it gave me when doing the work I studied to do it got in the way.
Most colleges I went to had special classes for students with perfect pitch as they were taught different strategies. In my final exam in "Gehörbildung" the two top scoring students did not have perfect pitch.
TI pretty clearly distinguishes between LDOs and other categories of linear regulators on the basis of using a FET pass element (which is true of neither the LM317 or the LM7800 series, both are Darlington-based).
It's not really clear from this paper, it is more handwavy based on today's circuits.
They claim that the darlington voltage drop is ~2V which is suitable for 5V to 2.5V regulation, and then introduce 100mV with an NFET as low-dropout for cases where LiPO cells are 3.6 V, or 300 mV above industry standard 3.3V (or the new embedded expectation of 1.8V or 1.2V off a 2x 700mV cells).
However, what if I need to regulate 3.35 V to 3.3 V, do I need an Even-lower LDO (ELLDO)? That meants we have HDO (2V), LDO (.1V), ELLDO (0.05V), which becomes an absurdly semantic situation.
I think the confusion is that engineers picked the words and it is based on the technology of a current point in time. In their mind, the breakpoint is NFET dropout of 100mV, which is purely subjective. Although I could also argue that my example is silly because it is within the range of tolerance of most datasheets spec for Vin of 3.3V +/- 1%.
I'll agree that it's largely a semantic difference and that I overstated the significance of the MOSFET involvement as the pass element - you can design single-transistor PNP elements with only a few hundred millivolts dropout, and at one point TI referred to these as LDOs.[0] Indeed, even the Sziklai pair gets called "quasi-LDO". Individual engineers likely have different personal thresholds for what constitutes an LDO. But it's worth pointing out that in practice there are only a handful of plausible linear regulator pass elements, and the physics of the BJT-based pass elements sort them into a distinctly higher minimum dropout voltage than what is achievable with MOSFETs.
I still stand by the characterization of LM317 and LM7800 family as "not LDOs". Both devices are Darlingtons with at least two Vbe drops across the series pass element. On the continuum of LDO------Not_LDO, both LM317 and LM7800 are firmly on the Not_LDO side.
They are not. They are inherently high dropout devices which is why LDOs were created in the first place. LDOs are a refinement on those early generation of linear regulators.
The rise of 3.3V devices created a demand to derive regulated power from a 5V rail. Traditional linear regulators are unsuitable for this because the dropout voltage is in the range of 2V. LM317, the most likely old school variable output candidate, is 3V drop and can't do the job either.
How often is the database updated? For instance on stock price data can it be considered realtime (or 15 min lag) for daily market tracking? Not familiar with that SEC api.
The data is refreshed nightly for stocks.
And monthly from SEC once it is available to download.
There is no guaranteed data delivery SLA that I know about from SEC, so I get it monthly once it arrives.
I talk more about this in detail on the website,
I will also update the data documentation tab, and in tutorials.
https://tesseractanalytics.ai/finance-data-quarterly-data-do...
Thank you! Yes, but I am using their monthly dumps for now, because it was easier for data warehousing.
I will put it in my plans to pull data daily incrementally in the future as a next phase.
Isnt the lock-in amplifier technique used to improve the SNR ratio of a signal by filtering out noise at frequencies outside a specific range of interest? High-speed sampling would still be required to accurately measure transient signals.
The harmonics of a guitar or piano can extend well beyond 8kHz, even though they contain lower frequency components that give them their characteristic sound. In fact, the higher harmonics can contribute to the richness and complexity of the overall sound, even if they're not heard as distinct pitches. Similar effect occurs with cymbals, the high-frequency shimmer of cymbals can extend well above 8kHz. Also violins can include overtones that extend beyond 8kHz and the sound of a trumpet can include overtones that extend up to 10kHz or higher.
Does U.S. law really require cookie pop-ups? And don't most websites store the cookies before consent is given anyways?
https://olivergrimsley.com/2022/03/04/please-stop-putting-co...