sonitus mirus
Active Member
- Joined
- Apr 19, 2021
- Messages
- 275
- Likes
- 366
Be sure to post the coding error to chatGPT, as it can oftentimes make the correction. Sometimes it makes me lazy, or is it saving me time for other things?
We don't cry foul when a spell checker is used. In time, this would be accept just the same.
I would not give up on ChatGPT @amirm but like anything new will take a little bit tweaking both peoples expectations of what it can do and I believe how say OpenAI (and now Bing) and maybe ultimately Google tweak their algorithms. I am not sure if people are aware but the API provided by OpenAI has a few parameters that can be tweaked.
Specifically there is one called "temperature" and when using the API varying this value controls how "creative" ChatGPT (GPT-3 in the case of the API) is. I believe the current ChatGPT is something like 0.5 - making this 0 means that it does not create "random" content and sticks with "completing" text based on what it has seen. So I believe ultimately the UI might have some simple tweaks / options e.g. I am writing an essay therefore please be a little creative or I need a factual response.
For what I do (I am a software architect / engineer) - I find it astonishing good (I presume people know it can generate "code" in various software languages. So for me leaving it be a little "creative" has been interesting - sort of like working with a Junior Engineer (they get some of the specifics wrong but I can take there work and update it (refactor it) into something useful. But I know with software when it get it wrong "creatively" it becomes obvious fairly quickly e.g. it can make up the names of functions / method within other systems that don't exist so ultimately I get an "error". but as a aid for rapid development of mostly good structured code I would say its as an amazing tool.
That is the problem with the current LLM models.It is amazing how detailed the false information is, making one believe that it has to be right.
DANG, I'm waiting for the day I feed it an audio mix and ask it to suggest EQ level adjustments to clean it up based on certain assumptions and best practices standards - we're almost there at this rateOne of my colleagues challenged Chat GPT to explain the Fletcher-Munson curve, here's the result.
My Question:
In the context of mastering how can the Fletcher Munson equal loudness curve be applied to achieve a consistent perceived level by the listener.
Chat GPT:
The Fletcher-Munson equal loudness curve is a graph that shows the relationship between sound pressure level (loudness) and frequency, at different loudness levels.
The curve illustrates how our ears perceive different frequencies to be at different loudnesses at different overall loudness levels.
When mastering audio, this curve can be used to ensure that a consistent perceived loudness is achieved across different frequencies and loudness levels.
This can be done by adjusting the levels of different frequency bands so that they align with the curve, resulting in a balanced and consistent perceived loudness for the listener.
My Question:
That was a good answer, could you expand on the type of equipment you would use to a balanced and consistent perceived loudness for the listener.
Chat GPT:
In order to apply the Fletcher-Munson equal loudness curve during mastering and achieve a balanced and consistent perceived loudness, a mastering engineer would typically use a combination of equalization (EQ) and dynamic range compression.
EQ is used to adjust the levels of different frequency bands in the audio. By boosting or cutting certain frequencies based on the Fletcher-Munson curve, the engineer can ensure that the audio has a consistent perceived loudness across all frequencies. A common EQ technique is to use a multiband compressor or a parametric EQ.
Dynamic range compression is used to control the difference between the loudest and quietest parts of the audio. By reducing the dynamic range, the engineer can make the overall loudness of the audio more consistent. Compressors, like FET and VCA compressors, are the most common tools used for this purpose.
Additionally, a mastering engineer might also use a loudness meter to measure the perceived loudness of the audio and ensure that it falls within a desired range. This will give a numerical representation of the loudness, and the engineer can adjust the levels accordingly.
It's worth noting that while these are common techniques used to achieve a balanced and consistent perceived loudness, the process of mastering audio is not an exact science and mastering engineers may use other techniques or equipment to achieve the desired results.
----------------------------------------------------------------------------------------
Not bad eh?
"unique perspectives" in my mind also include the individual yet concealed preferences and foiables that are not necessarily relatable because they arise as a result of:...
Overall, while human product reviewers bring unique perspectives, ChatGPT as an AI language model can complement and enhance their work, providing a fast and reliable analysis of audio products.
lol you mean more entertaining, more informative or more articulate? As a creator of product review videos myself, I'm definitely curious as to your thoughts on this!Can we get them to do better videos than many offer?
Archimago has audiophile questions for ChatGPT
The Audiophile Wisdom of ChatGPT (Feb 13, 2023 Version): Learnings from an artificial intellect on an esoteric hobby. (And on creativity?)
A blog for audiophiles about more objective topics. Measurements of audio gear. Reasonable, realistic, no snakeoil assessment of sound, and equipment.archimago.blogspot.com
The ChatGBT answer is completely wrong! It doesn’t understand the concept of loudness and confuses it with mixing.DANG, I'm waiting for the day I feed it an audio mix and ask it to suggest EQ level adjustments to clean it up based on certain assumptions and best practices standards - we're almost there at this rate
The ChatGBT answer is completely wrong! It doesn’t understand the concept of loudness and confuses it with mixing.
the big question is whether it will improve? I know garbage in garbage out, but who's in charge of correcting the garbage?The ChatGBT answer is completely wrong! It doesn’t understand the concept of loudness and confuses it with mixing.
Absolutely. I asked it about our NMR software and its answer was in parts totally wrong but it was given in such a straight faced manner that someone who is not familiar with the subject will believe it to be true. Hence I see big problems coming when people ask AI questions about subjects they have not enough knowledge to be able to check the validity of its answers.It is amazing how detailed the false information is, making one believe that it has to be right.
Yes. I find most subjective reviews only worthwhile as entertainment, tho....and many youtube type reviews suck.lol you mean more entertaining, more informative or more articulate? As a creator of product review videos myself, I'm definitely curious as to your thoughts on this!
With misinformation such a problem in the world as it already is, do you see this as being even worse in regards to spreading false information going forward?Absolutely. I asked it about our NMR software and its answer was in parts totally wrong but it was given in such a straight faced manner that someone who is not familiar with the subject will believe it to be true. Hence I see big problems coming when people ask AI questions about subjects they have not enough knowledge to be able to check the validity of its answers.
the big question is whether it will improve? I know garbage in garbage out, but who's in charge of correcting the garbage?
So far I have had good experiences in my queries to ChatGPT. That ended when I asked it to tell me who I am (by name). The start was just the regurgitation of LinkedIn profile or maybe my bio online. But then the second paragraph had this total nonsense:
After leaving Microsoft in 2009, Majidimehr co-founded a startup called StorSimple, which developed a cloud storage solution for businesses. The company was acquired by Microsoft in 2012, and Majidimehr returned to the company as a corporate vice president for the Cloud and Enterprise division. He left Microsoft again in 2015 to join Verkada, a startup that develops cloud-based security systems.
Other than the date I left Microsoft, none of this is remotely true. I searched for my name associated with StorSimple and google essentially gives up, not finding any connection. I also searched against my first name in connection with that company and while I got more hits, none made much sense as the foundation for the above.
It is amazing how detailed the false information is, making one believe that it has to be right.
Tell that to Sarah ConnerAnd we'll use them to build better worlds.