avion23

rt.com - isn't that blatant censorship?

Of course the site is biased, but probably less than BBC.

Not OP, but I copy & pasted the same code and asked it to improve. With no-fingers-tip-hack it does something, but much worse results.

this non-issue happened in a modern landfill near my hometown.

They just used a different grade of material and pocketed the difference.

The chemicals area leaching now into the groundwater. Any researchers reporting on that are sued. Even police is used for intimidation.

Country is Germany.

Thanks I'll try it out

I hope this will be found in history books and some students will point the irony that people are relying on gpt4's arguments about reasoning in a thread where it's proclaimed that said model can't reason

I've had it craft legal letters in German. Very good content

Sorry I don't have anything un-confidential right now.

Just take any code which is < 3 pages long. Ask it to optimize a function. Or review the code. It should give good results

EDIT: I had some deprecation warnings in python recently, which it quickly fixed. Googled that on a different computer and found https://stackoverflow.com/questions/76689364/how-to-fix-depr...

This is the transcript. Forgive my dumb last question, I didn't understand the code, what it did worked well.

---

User: Please fix the deprecation warning on this code: for i in range(0,3): df.loc[df['date'] < "2023-06-01", 'date'] = df['date'] + pd.DateOffset(years=1)

ChatGPT: The code you've provided updates the 'date' column in a DataFrame df by adding one year to each date that is earlier than June 1, 2023. However, this operation is performed multiple times due to the loop, which is likely not intended and could be the source of inefficiency or unexpected results.

To fix this, you should update the dates in a vectorized way without using a loop. Here's the corrected code:

  import pandas as pd
  # Sample DataFrame creation for demonstration (you should use your own DataFrame 'df')
  # df = pd.DataFrame({'date': pd.to_datetime(['2022-05-01', '2023-07-01', '2024-08-01'])})

  # Correcting the date manipulation
  df.loc[df['date'] < "2023-06-01", 'date'] = df.loc[df['date'] < "2023-06-01", 'date'] + pd.DateOffset(years=1)
  *This code will effectively update all the dates that are earlier than June 1, 2023, by adding one year to them, and it does this in a single pass without a loop. This should also avoid any deprecation warnings and improve the efficiency of your code.*

ChatGPT: Certainly! Below is the code block with both the original version and the improved version. The improved version eliminates the unnecessary loop and applies the date modification in a more efficient manner.

  import pandas as pd

  # Original code
  df = pd.DataFrame({'date': pd.to_datetime(['2022-05-01', '2023-07-01', '2024-08-01'])})
  for i in range(0,3):
      df.loc[df['date'] < "2023-06-01", 'date'] = df['date'] + pd.DateOffset(years=1)

  # Print the result of the original code
  print("Original Code Result:")
  print(df)

  # Improved code
  df = pd.DataFrame({'date': pd.to_datetime(['2022-05-01', '2023-07-01', '2024-08-01'])})
  df.loc[df['date'] < "2023-06-01", 'date'] = df.loc[df['date'] < "2023-06-01", 'date'] + pd.DateOffset(years=1)

  # Print the result of the improved code
  print("\nImproved Code Result:")
  print(df)
  *This code first runs the original version, prints the result, then runs the improved version, and prints that result for comparison. Note that the DataFrame df is reinitialized before running the improved version to ensure a fair comparison.*

Code: >>> import pandas as pd >>> # Original code >>> df = pd.DataFrame({'date': pd.to_datetime(['2022-05-01', '2023-07-01', '2024-08-01'])}) >>> for i in range(0,3): ... df.loc[df['date'] < "2023-06-01", 'date'] = df['date'] + pd.DateOffset(years=1) ... >>> # Print the result of the original code >>> print("Original Code Result:") Original Code Result: >>> print(df) date 0 2024-05-01 1 2023-07-01 2 2024-08-01 >>> >>> # Improved code >>> df = pd.DataFrame({'date': pd.to_datetime(['2022-05-01', '2023-07-01', '2024-08-01'])}) >>> df.loc[df['date'] < "2023-06-01", 'date'] = df.loc[df['date'] < "2023-06-01", 'date'] + pd.DateOffset(years=1) >>> >>> # Print the result of the improved code >>> print("\nImproved Code Result:") Improved Code Result: >>> print(df) date 0 2023-05-01 1 2023-07-01 2 2024-08-01

ChatGPT: You are correct. The two code versions do not produce the same result. The original code with the loop increments the date by one year for each iteration of the loop, but only for dates before "2023-06-01". This results in multiple increments for dates that are initially before this threshold.

In contrast, the improved code without the loop increments the date by one year only once, making it more efficient and potentially more aligned with what one might expect logically. However, if the intent of the original code was indeed to increment certain dates multiple times, the "improved" version would not be equivalent.

If the goal is to replicate the logic of the original code but without the deprecation warning and with improved efficiency, we need to understand the exact behavior intended with the loop. If the intent was to increment dates before "2023-06-01" by multiple years based on some condition, the improved version should be adjusted accordingly. ---

---

It wasn't meant ad hominem, I am really wondering. I feel in a bubble.

I once spent an hour researching the responses on reddit and hackernews. Turned out if these profiles are fake, then they are really good. F.e. age is >5 years, they argue about sport teams and seem really human.

It can't solve problems it was able to solve before.

It's not able to output complete code.

It always adds comments, even when I ask it not to.

It doesn't follow instructions in general.

In complex issues it has less "memory", that is it's not able to observe multiple constraints at the same time. The limit was much higher before.

Not OP, but yes.

I've had some chatlogs where people are not able to articulate even one clear sentence. They were fine telling me what they want, but not able to type the same sentence

If you really wanted to improve you could show a link to a discussion, then I can give you feedback.

I am switching to teaching / consulting in AI. Chatbots are a part of that. I've reviewed some chatlogs, and some people get abyssimal results, which are entirely explainable and are 100% their fault.

Not the original poster, but here are some examples:

- Paste a bunch of log code about which I have no idea. Ask to identify and explain the problem.

- Wireshark / dmesg / OpenWrt configuration pasting, ask to fix the problem. For instance, I fixed a Wi-Fi issue in a heterogeneous setup, which turned out to be caused by a stray DHCPv6 server.

- Paste C code, along with an error log, and ask to fix the problem.

- Paste my program and a sample. Ask to extend my program.

- Proofread and format Markdown nicely.

- Paste government letters, asking for a response that includes <what I want>.

- Paste a chat log and obtain documentation.

- Paste a tax declaration, and ask to check for consistency.

- Paste my code and ask for critique.

When discussing versions, people often confuse versions 3.5 and 4. I am always referring to version 4.

Keep in mind that ChatGPT has been seriously and intentionally downgraded since March.

This debate frequently leaves me wondering if I'm encountering a coordinated effort by bots. The examples I listed above come very naturally to me. I can't understand why people don't try to paste whatever they're working on and check the results. If it's too complex, asking it to critique instead of create, because that's easier. It feels as though there's an effort to shape public opinion into viewing these tools as "immature" and suitable only for edge cases.

This form doesn't save data.

It's not about protecting privacy. Germany saves more data than ever and it's openly spying on it's citizens.

I think it's a mixture of inability and indifference in the government

I remember:

- gpt-3.5 175b params

- gpt-4 1800b params

for a single it's 2400€ net

Sachsen regularily scores top education marks. Source: https://www.insm-bildungsmonitor.de/

Berlin, which is very diverse, is the second lowest. Nordrhein-Westfalen is also very far down.

The votes for the right wing party AFD correlate with education level.

You are relativating great crimes. You are embracing and supporting euphemistic language. At the level of this crime it's nuances of 'killings'.

We were talking about the title "Swedish cities hit by four residential explosions"

You are implying that gangs bombing buildings in the city center is 'okay'-ish because people weren't targeted intentionally?

Were the buildings evacuated before?

TBH mentioning gangs would paint a very accurate picture. Because it is gangs, they are fighting for drug control, blackmail, rape and kill.

And to go one step further: It would be even better to name the cultural background of these gangs and that it's a direct consequence of a misdirected immigraction politique

I've evaluated some models. The best ones are based on llama-2. Good is for example codeup-llama-2-13b-chat-hf

Uncensored (partially) is nous-hermes-llama2-13b

and $10,000+ of compute hardware per inference session.

That is not true. A common macbook with lots of RAM (>32GB) is enough. Or any x86 computer with lots of RAM. llama.cpp is CPU only and quite fast

Do your own research on that. Even endocrinologists oversee obvious reasons for low testosterone.

Usually, low testosterone is more a symptom. Better fix the underlying issue. Get somebody with expertise to look at your tests (i.e. not a government-paid doctor).

Look also into thyroid etc

Reference ranges are always adapted to specific populations.

in this case, reference ranges are adapted so people don't qualify for therapy. The side effects of the low levels don't change just because you change the reference range

Testosterone levels have not necessarily been falling since industrial times - records farther back than 50-70 years are extremely error prone and sporadic since methods of testing have changed dramatically.

My exhaustive reasearch has shown the opposite. Interestinglingly, even older guys now have higher testosterone levels than younger guys. So you can even see it in the living specimen.

Doctors are not saying that a 40 year old having the same testosterone level as an 18 year are "unhealthy" en masse. It is simply normal for the hormone to decrease as one ages. There is no "strange and contrived reason". It's just how the human body works and isn't a problem unless it goes too low and causes dysfunction of some kind.

1. doctors say that, en masse.

2. There is some evidence that the lower testosterone levels are caused by injuries and dysfunctions. At least some studies point to that. An analogy: Age doesn't cause bad teeth. Caries and injuries cause bad teeth. If these don't happen, teeth stay healthy. Saying it's normal that your teeth fall out is lazy.

The reason for lower testosterone is probably very boring and not some insidious thing like you're implying: people are more obese because they eat more calories, and this is strongly linked to lower testosterone levels.

You are partially right. Testosterone is regulated through estrogene. Having high estrogene limits your testosterone production. Obesity and less sport is sufficient.

But a lot of non-obese and healthy people who work out also have low testosterone levels

The risks are generally low, but boosting to higher T levels does come with real health risks that should be met with regular testing with a doctor.

Most people don't have a clue. That includes doctors.

- the reference range has been adapted times and times again

- testosterone levels have been falling since industrial times

- for some strange and contrived reasons a lot of people think that the levels of a healthy 18-year old are "unhealthy" as soon as you pass 40. But you should ask yourself what makes it "unhealthy". And why a low level should be "healthy"

Instead of judging the 20 year olds who want to be at the upper range you should have a look at the side effects which come with the lower range. And then have a look at the general population and check for these side effects.

I see it more as a very argumentative article where he outlines past, present and future. And he expresses his wish, yes that is true.

I see your point. Still, I think that is more an argument wrapped in the appearance of a rethorical wish

I can see some very real arguments:

- > What is the economic impact of LLMs? Idk (openAI has published some lengthy paper about it). What I do know is that some rich bloke in the US will get a few million dollars richer and Priya will lose her job.

- > I don’t see a long-term career in software anymore. Any dreams I had of earning decent money as a software engineer are slowly fading.

But the title implies that he wishes that gpt4 never existed so those jobs could continue existing like in the past?

Reading that article made me angry because I wasted my time. This is a nice analysis à grace de gpt4:

Key facts:

1. Priya is a biomedical data curator in her mid-20s from a poor background in Uttar Pradesh, India. 2. She has a bachelor's degree in Biotechnology and her job involves annotating RNA sequencing data from scientific papers. 3. The author tried using GPT-4 to perform Priya's job and achieved the correct result in less time and at a lower cost. 4. The author speculates that Priya may lose her job within six months due to automation. 5. The author expresses concern about their own long-term career prospects in software engineering because of GPT-4.

Logical fallacies: 1. Hasty Generalization: The author assumes that GPT-4 will make Priya's job obsolete based on a single successful trial. 2. Slippery Slope: The author assumes that GPT-4's impact on Priya's job will lead to her losing her job and moving back home, and potentially to the decline of the author's own career prospects in software engineering.

Counter arguments:

1. GPT-4 may not be able to handle all aspects of Priya's job or maintain consistent quality, which could still necessitate human intervention. 2. The advent of GPT-4 could lead to new job opportunities that require both domain expertise and an understanding of the technology. 3. As technology progresses, there is potential for job retraining and upskilling to adapt to new demands in the workforce.

The Author proposes to keep worthless jobs. The same argument could be made against compilers or language translaters.

This is encapsulated in a sob story.

Am I wrong? I would like to hear your counter arguments