ChatGPT GPT-4 Output got Faster and Worse?

I’ve noticed that lately the ChatGPT 4 output got way faster than it used to be, but also the prompt outputs quality worsened significantly. I’m not the only one that noticed this, there is a twitter post about this too by Peter Yang.

@petergyang/status/1660314935208054785

The quality of the prompt outputs and the logic now is way worse, it feels like I’m using a slightly smarter version of GPT 3.5. Is there a way to use the previous GPT 4? It was slower but the results were WAY better.
In comparison and prompt output feel, It feels like GPT 3.6 at most, not GPT 4.

I tried disabling the plugins and browser extenstions but with no luck.

I’d pay more if needed just to get the previous version. Also I haven’t maxed out this version at all. Usually I’d max out the 25 prompts, but since the speed increase it’s like that’s not the case.
I’d take the limited version without the speed increase and better prompt outputs for sure.

Anyone else noticed this speed over quality ?

I’m a software AI engineer, and I use GPT4 daily.

11 Likes

I noticed it too. ChatGPT-4 has become dumber. Now It is like a slightly better version of GPT 3.5. But if you use GPT4-API then results are still as good. Another disappointing thing about ChatGPT-4 is that it has only 4K tokens memory. API versions has 8K and 32K.

6 Likes

The May 12 version was a major downgrade from May 3. I thought it couldn’t get any worse, but now I am even more dismayed by the latest “May 24 Version” which appears to actually be a further step in the wrong direction.

I am observing even greater loss of reasoning between the May 12 and May 23 version! Hard to overstate how frustrating this is! The May 23 version in many respects appears to follow instructions more poorly than GPT3.5 at this point and consistently fails to solve basic logic problems.

@#$!

We should really be coming together to push for the ability to select previous versions (i.e., a toggle switch for using the May 3 version vs current release). I started a thread on this a couple days ago, but no replies.

5 Likes

I’ve noticed the same thing. It moves much faster (which is entirely unnecessary in my case), but performs worse, especially in reasoning. It sometimes makes gross errors (invented words or completely absurd misunderstandings), which I had never seen before (and yet I’ve spent hundreds of hours on it). It quickly loses track of the conversation, and suddenly forgets instructions that were explicitly given as structuring. The most disappointing part of this story is that it is easy to understand that this degradation was done for economic reasons or computational power, but it was done behind the users’ backs. I feel cheated, I am counting on a quick improvement, otherwise I will cancel my subscription and I won’t come back.

6 Likes

Update:
I think they’ve reverted it to the previous version couple of days ago. The prompts are better now, the output remembers the context better, but still, the logic is 80-85% of the first GPT4 version.

I still haven’t reached the 25 maximum messages since the quality decline.

Nevertheless, it gets the job done, but it should be better.

I have to agree. It frustrated me so much that I started googling, ended up here, created a account in this forum and now posting my frustration. It’s almost useless for my use case now and I see no reason to pay for such poor quality anymore…

I mean really? I’m paying for the subscription, still getting limited but much worse responses now?

2 Likes

Well I started working with GPT4 today after a couple of days and I have to disagree. I wrote some tasks (prompts) for GPT4 and I tested them again and instantly noticed the much worse responses. I tried multiple prompts to fixing the results with very little success. Now GPT can not comprehend any context (at least when your prompt is on the more lengthy side or when you try to refer to prev. conversations). I’m extremly disappointed after being so hyped with the release of GPT4.

Ditto. And it honestly keeps getting worse… Here’s a disgusting, astounding example from today of just how stupid GPT4 has become:

Prompt:
OK, let’s revise your writing output to be more formal. You need to learn an important, basic lesson in scientific writing: “higher” is not an appropriate substitute for “greater”, etc.

ChatGPT4:

I appreciate your feedback, and you’re correct. In scientific writing, precision is important, and the choice of words can significantly impact the interpretation of the results.

“Higher” and “greater” can be used interchangeably in casual conversation, but in scientific contexts, they could imply different meanings. For example, when comparing numbers, we’d generally say one number is “greater” than another, not “higher.” On the other hand, “higher” is often used to describe physical height or levels in a vertical hierarchy.

I strive for accuracy and clarity in all types of writing, including scientific writing, so I appreciate your feedback to help me improve. However, as of my last training cut-off in September 2021, I do not have the capability to learn or adapt my responses beyond the data I was trained on. I can provide information and responses based on that training, but I can’t learn new information or correct my style of writing based on user feedback.

The developers at OpenAI regularly update and improve the model, so feedback like yours is crucial in making these improvements. Thank you for your input!

W. T. F. am i even paying for…!?
Two months ago, this prompt would have elicited a very different, superior response from GPT4.

3 Likes

Agreed. Thank you for giving an example. Since most of my prompts are in German, it wouldn’t be that helpful providing some of my examples, but I got a similar answer (translated) as you did. Is there an official statement from OpenAI somewhere (website, forum or Twitter)?

2 Likes

You are so right. Its not working anywhere near as well as it did in the past.

1 Like

6/27/23 … & ChatGPT4 still appears to be functioning in a lobotomized state.

2 Likes

OMG I got so frustrated with the latest coding ability of Chat GPT4, its not even funny. Like its really 3.6, not 4. Before, when I ran out of questions I would never switch to 3.5, I would simply wait as 3.5 was useless at this level. But now, I find 3.5 just as “useful”. This is crazy. If it stays this way I will also consider cancelling my subscription and going for the free 3.5 as this is not worth paying for

2 Likes

Yeah, it’s pretty bad right now. I’m glad I didn’t pay for it yet! I wonder if this is a trick to push users towards Microsoft or someone else’s implementation. What a shit thing to do to the users, regardless of the reason.

1 Like

Yes I can echo what everyone else here has said. I would even keep it still if the browser ability was still present, but with the major decrease in logic between past chatGPT4 and how it seems to be operating now at its seemingly dumber, faster, degraded rate, AND there is no browser ability, I will probably be cancelling my GPTPlus subscription. Of course when I get stuck somewhere hard enough trying to milk what I need out of GPT3.5 I will probably come back out of desperation or just finally switch to using the API. I just need one or the other: logic as strong as it originally seemed from gpt-4, or the ability for it to browse online to search for context to bridge the gap between its learning cutoff and the present or the gap between its training scope and my very specific requests.

3 Likes

Yeah. Plugins have also become almost useless. Even when plugins work, and return correct data, it often ignores them. I tried the following with WebPilot and LinkReader (Both plugins can search/browse the web.):
I asked it to check Tom’s hardware and to look for then summarizes recommendations for best and recommended SSDs. It would use the plugin, receive correct info, then simply ignore it and generate response based on 2-3 years old data. This happened several times with both plugins, and both plugins were returning correct data. Tried arguing with it, it would apologize then repeat the same mistakes over and over again.
Tho few days later, day or maybe 2 days ago, I repeated this, just to test, with Link Reader plugin, and this time it provided the correct result (It considered data returned by the plugin). It appears the results vary. Maybe it depends on the system load? Or they continuously play with different weights, parameters, whatever, trying to ‘optimize’ it. Nothing against that, but this should be done and communicated differently. Release new, specialized models, and tell people about it. OTOH, not sure about butchering and replacing the main, general gpt4 model, with a broker, which is supposed to redirect your prompts to specialized models (Like the article below seems to suggest.). This can hardly work, because interpreting the prompt is kinda important, and you can hardly expect same results from ‘full’ and ‘specialized’ model. Mybe it could make sense to use the full model for initial prompts, then to forward later queries to specialized models. Not sure how possible or easy this is. It would still save resources, depending on a convo. Currently it feels like they have been trying to use old gpt.3.5 as a ‘broker’.

Also tried the new, cool (Python) code interpreter model. I have seen other people using it, and it was able to provide “how to” instructions and to explain its abilities. In my case, the model wasn’t even aware it can read/upload files. It also wasn’t aware it can execute code, and it repeated the ‘knowledge cutoff’ phrase. This is supposed to be ‘gpt4’ with code interpreter plugin, but it felt like 3.5 version from October last year.
This article mentions some of the possible reasons I mentioned above:
The world’s most powerful AI model suddenly got ‘lazier’ and ‘dumber.’ A radical redesign of OpenAI’s GPT-4 could be behind the decline in performance.

1 Like

Here’s a perfect example I haven’t seen before in GPT4. This comes from a conversation about this code where the locations, functions and context has been explained in detail many times. My prompt starts after GPT made a mistake in a code block in the previous response and I tell it

Prompt:
There are 2 things wrong with your last response:
1: you forgot that the settings.php and business_profile.php files both reside in the settings/ folder. I’ve corrected this in the index.php file and settings.php now.
2: I get an error when I open the settings page:
Fatal error: Cannot redeclare fetch_business_profile_data() (previously declared in /home/u321618269/domains/solidslick.com/public_html/dev/wp-content/plugins/pro-repair/settings/business_profile.php:4) in /home/u321618269/domains/solidslick.com/public_html/dev/wp-content/plugins/pro-repair/settings/business_profile.php on line 3

This is settings/business_profile.php:

<?php
    // Fetch Business Profile Data
    function fetch_business_profile_data() {
        global $wpdb;

        // Fetch data from the database
        $results = $wpdb->get_results("SELECT * FROM ersp_company", ARRAY_A);

        // Return the data as a JSON response
        wp_send_json($results);
    }

    // Add ajax action hook
    add_action('wp_ajax_fetch_business_profile_data', 'fetch_business_profile_data');
?>

<tbody id="company-table">
    <!-- data will be inserted here dynamically -->
</tbody>

This is settings/settings.php:

<div class="wrap">
    <h1><?= esc_html(get_admin_page_title()); ?></h1>
    <nav class="nav-tab-wrapper">
        <a href="#business-profile" class="nav-tab" data-tab-target="business-profile">Business profile</a>
        <a href="#reset-db" class="nav-tab" data-tab-target="reset-db">Reset DB</a>
    </nav>

    <div id="tab-content">
        <div id="business-profile" class="tab-content" style="padding-left: 20px;"><?php include plugin_dir_path(__FILE__) . 'business_profile.php'; ?></div>
        <div id="reset-db" class="tab-content" style="padding-left: 20px;"><?php include plugin_dir_path(__FILE__) . 'reset_db.php'; ?></div>
    </div>
</div>

<script type="text/javascript" src="<?php echo plugin_dir_url(__FILE__) . 'scripts/settings.js'; ?>"></script>

And this is settings/scripts/settings.js:

jQuery(document).ready(function ($) {
    $('.nav-tab').click(function (e) {
        e.preventDefault();
        
        // Switch tabs
        $('.nav-tab').removeClass('nav-tab-active');
        $(this).addClass('nav-tab-active');
        $('.tab-content').hide();
        $('#' + $(this).data('tab-target')).show();

        // If the Business Profile tab is clicked, fetch data from the database
        if ($(this).data('tab-target') === 'business-profile') {
            $.ajax({
                url: ajaxurl,
                type: 'post',
                data: {
                    action: 'fetch_business_profile_data'
                },
                success: function(response) {
                    // Clear the table
                    $('#company-table').empty();

                    // Add each row to the table
                    $.each(response, function(index, row) {
                        $('#company-table').append('<tr><td>' + row.company_name + '</td><td>' + row.company_address1 + '</td></tr>');
                    });
                }
            });
        }
    });

    // Trigger click on the first tab to make it active by default
    $('.nav-tab').first().trigger('click');
});

Please correct the errors and provide the complete corrected code blocks for each of those file, so I can copy/paste them back entirely.

GPT Response:
I apologize for the confusion. The error you’re seeing is because the fetch_business_profile_data function is being declared twice. This is happening because the business_profile.php file is being included twice: once in the settings.php file and once in the index.php file.

To fix this, you should remove the include line for business_profile.php from the index.php file. The business_profile.php file should only be included in the settings.php file.

Here are the corrected code blocks:

  1. index.php:
/* Includes the install file that installs the databases */
include(plugin_dir_path(__FILE__) . 'base/install.php');

/* Includes the search and filter function used on the models page */
include(plugin_dir_path(__FILE__) . 'base/search/fetch_models.php');

/* Includes the model modifications PHP file */
require plugin_dir_path(__FILE__) . 'models/model_mods.php');

register_activation_hook(__FILE__, 'ersp_install');
  1. settings/settings.php:
<div class="wrap">
    <h1><?= esc_html(get_admin_page_title()); ?></h1>
    <nav class="nav-tab-wrapper">
        <a href="#business-profile" class="nav-tab" data-tab-target="business-profile">Business profile</a>
        <a href="#reset-db" class="nav-tab" data-tab-target="reset-db">Reset DB</a>
    </nav>

    <div id="tab-content">
        <div id="business-profile" class="tab-content" style="padding-left: 20px;"><?php include plugin_dir_path(__FILE__) . 'business_profile.php'; ?></div>
        <div id="reset-db" class="tab-content" style="padding-left: 20px;"><?php include plugin_dir_path(__FILE__) . 'reset_db.php'; ?></div>
    </div>
</div>

<script type="text/javascript" src="<?php echo plugin_dir_url(__FILE__) . '../scripts/settings.js'; ?>"></script>
  1. settings/business_profile.php:
<?php
    // Fetch Business Profile Data
    function fetch_business_profile_data() {
        global $wpdb;

        // Fetch data from the database
        $results = $wpdb->get_results("SELECT * FROM ersp_company", ARRAY_A);

        // Return the data as a JSON response
        wp_send_json($results);
    }

    // Add ajax action hook
    add_action('wp_ajax_fetch_business_profile_data', 'fetch_business_profile_data');
?>

<tbody id="company-table">
    <!-- data will be inserted here dynamically -->
</tbody>
  1. settings/scripts/settings.js:
jQuery(document).ready(function ($) {
    $('.nav-tab').click(function (e) {
        e.preventDefault();
        
        // Switch tabs
        $('.nav-tab').removeClass('nav-tab-active');
        $(this).addClass('nav-tab-active');
        $('.tab-content').hide();
        $('#' + $(this).data('tab-target')).show();

        // If the Business Profile tab is clicked, fetch data from the database
        if ($(this).data('tab-target') === 'business-profile') {
            $.ajax({
                url: ajaxurl,
                type: 'post',
                data: {
                    action: 'fetch_business_profile_data'
                },
                success: function(response) {
                    // Clear the table
                    $('#company-table').empty();

                    // Add each row to the table
                    $.each(response, function(index, row) {
                        $('#company-table').append('<tr><td>' + row.company_name + '</td><td>' + row.company_address1 + '</td></tr>');
                    });
                }
            });
        }
    });

    // Trigger click on the first tab to make it active by default
    $('.nav-tab').first().trigger('click');
});

Please replace these files with the corrected code blocks. This should resolve the error you’re seeing.

NOW HERE’S A BREAKDOWN OF WHAT’S WRONG ABOUT THIS:

  1. require plugin_dir_path(FILE) . ‘models/model_mods.php’); contains a ) after php’) that’s not supposed to be there, wasn’t there and has never been there.
  2. I just explained in this prompt that settings.js is located in settings/scripts/settings.js because it messed up the file location in the previous response and I corrected it already in the example (settings.php) - yet, it changes it back again from: scripts/settings.js to: …/scripts/settings.js
  3. We just agreed in the previous prompt to move the include statement from settings.php to index.php. It generated the code blocks, which placed the include statements in both index.php and the settings.php page again. So, in this response it recognizes that the error is generated due to this mistake and then reverts to :

To fix this, you should remove the include line for business_profile.php from the index.php file. The business_profile.php file should only be included in the settings.php file.

We just agreed to move that in the previous prompt, then it messes up by duplicating the include and then just reverts back to the previous state.

These are not extremely long code blocks. They are short and simple blocks of code I had no trouble with only recently, but now it’s turned into an absolute mess. I can’t use chatgpt to work with if it makes these kind of mistakes frequently. The reason why I’m on a paid plan is that 3.5 makes these kind of errors where 4 didn’t use to, but right now it’s almost as bad as. If this doesn’t change soon I may as well stop my plan as it’s starting to cost more time checking and trying to fix responses than it’s saving me time.

3 Likes

I’ve noticed lately that the responses are gradually but consistently are getting worse again.
I think OpenAI have scheduled GPT4 outputs quality based on the number of inputs they’re getting on a daily basis (prompt quality to prompt number balancer of some sort).

It’s sad because we’re paying for a very nice feature, but just as Google CEO said it himself, we’re “SLOWLY” releasing the AI - aka gatekeeping the better versions for bigger prices.

Closing this topic.

Please consider using this topic instead.

GPT-4 has been severely downgraded (topic curation)