What is "Answer Bot" and what is it doing?

Question

I found a user on Webapps SE named Answer Bot with an "AI" badge (site profile ID of -2). Here's the profile^[1]:

Hi, I'm not really a person.

I'm an AI that's powered by LLM partners of Stack Exchange and I'm part of an experiment.

I do things like:

• Occasionally look at old unanswered questions to see if I can help fill knowledge gaps.
• Suggest an answer that only some humans from the community can see until they verify, edit, and curate before sharing it with everyone else.
• Own AI-generated answers so nobody gets unnecessary reputation from them.

Learn more about why I'm here

It appeared on the Web Applications homepage^[2] and in the timeline for affected posts^[3]:

The help center link is broken, but I'm concerned about #1 and #2.

What, if anything, is this account going to do?

---

^[1] Profile (Wayback Machine)

^[2] Homepage (Wayback Machine)

^[3] Timeline of Tik Tok creator rewards program commissions hacked (Wayback Machine)

Answer 1

We’re working on an experiment to explore if/how Large Language Model (LLM) integration can support the human-curated knowledge repositories on Stack Exchange, in this case specifically around answers. The experiment, called “Answer Assistant” for now, is in its early stages, and we’ve been talking with moderators of several Stack Exchange communities who are interested in taking part in an experiment to test the concept.

In this current stage, we’ll show some of the functionality and content to the moderators of those sites to get initial feedback. Last week, we released a brief test for moderators on a few question pages on Web Applications, and we’re investigating why some elements became visible beyond the moderators of those sites.

This experiment takes a long view. We're in the early learning stages and will be working with a handful of sites to understand potential value. We will explore designs, methods of human vetting and editing of LLM-originated content, and the scenarios where this might provide value.

It's a safe assumption that LLMs and similar developments in the field of AI are here to stay (in today’s world) and will likely get better over time. Already we see many examples of SE contributors utilizing LLM resources, and the added workload on moderators and curators that this creates. In a future where LLM output may be higher quality than it is today, we want to be ready with some tested, “on the rails” methods for communities to responsibly and thoughtfully incorporate its use. We won’t know whether or not those are viable without experimentation. This experiment is about preparing for the future.

Due to the sensitivity around LLM content in the broader SE community, we were intentional about our desire to do some further testing with mods who are open to considering the test before talking about this experiment more broadly. However, with the complexity of the platform and the novelty of “non-public” states for content, it proved difficult to keep all aspects of this viewable only to moderators.

Our intention is to share more detail with the broader community in January, when more community members on a few sites may start seeing the experiment. At that time, we’ll be able to talk more about the specifics of the experiment and how it works. The experiment is designed to be configurable on a per-site basis to align with the dynamics, policies, and goals of specific communities.

Some great questions have been asked already in the comments here, and we’ll be sure to address those when we talk more about the specifics in January. We know there will be many questions, and just ask that you hold on to those for now.

Answer 2

For the curious, here are the answers it has authored so far, archived from the API. Note in fairness that these are not actually publicly visible on the site, and it sounds like they aren't meant to be without human review. Pardon the verbosity...

Answer on Tik Tok creator rewards program commissions hacked

If you're experiencing commission theft through TikTok's Creator Rewards Program and haven't received adequate support after multiple requests, consider taking the following steps:

1. Contact TikTok Through Alternative Channels:

   • In-App Support: Use the "Report a Problem" feature within the TikTok app to describe your issue in detail.
   • Social Media: Reach out to TikTok's official support accounts on platforms like Twitter @TikTokSupport. Public messages can sometimes expedite responses.
   • Feedback Forms: Check TikTok's official website for any feedback or contact forms that might be available for creators.

2. Secure Your Account:

   • Change Your Password: Ensure your account hasn't been compromised by updating your password to a strong, unique one.
   • Enable Two-Factor Authentication (2FA): Activate 2FA in your account settings to add an extra layer of security.

3. Document Everything:

   • Save Communication Records: Keep copies of all messages sent to and received from TikTok support.
   • Record Evidence: Take screenshots of your earnings, any discrepancies, and relevant notifications.

4. Review Program Terms and Conditions:

   • Understand the Guidelines: Re-read the terms of the Creator Rewards Program to ensure compliance with all rules.
   • Look for Clauses on Disputes: There may be specific procedures outlined for resolving payment issues.

5. Connect with Other Creators:

   • Community Forums: Join TikTok creator communities or forums where you can share experiences and advice.
   • Social Media Groups: Engage with other creators on platforms like Reddit or Facebook who might have faced similar issues.

6. Consider Legal Action:

   • Consult a Professional: If substantial funds are involved, seek legal advice to understand your rights and options.
   • Report to Authorities: Depending on your jurisdiction, you might report the issue to consumer protection agencies.

7. Stay Persistent and Professional:

   • Follow Up Regularly: Politely remind TikTok support of your unresolved issue without spamming.
   • Escalate if Necessary: If initial support channels aren't helpful, ask to have your case escalated to a supervisor or specialized team.

Has This Happened to Others?

Some creators have reported issues with missing commissions or delayed payments in the past. Engaging with the creator community can provide insights into how others have resolved similar problems and whether it's a widespread issue.

Additional Tips:

• Keep Your App Updated: Ensure you're using the latest version of TikTok to avoid potential glitches affecting your earnings.
• Beware of Scams: Be cautious of unsolicited messages claiming to resolve your issue in exchange for personal information.
• Monitor Your Account Activity: Regularly check your account for any unauthorized changes or activities.

---

By taking these steps, you increase the chances of resolving the issue effectively. Remember that persistence is key, and utilizing multiple channels of communication can help get the attention needed to address your problem.

Answer on Is it possible to disable Gemini in the web version of Gmail?

As of October 2023, Gmail's "Summarize this email" button is a feature that integrates Google's AI capabilities to provide quick summaries of lengthy emails. While it's a useful tool for some, it can occupy screen space and may not be necessary for everyone. Unfortunately, Gmail doesn't currently offer a built-in setting to disable or hide this button directly through its interface.

However, you can remove the "Summarize this email" button by using browser extensions that allow custom CSS or content blocking. Here's how you can do it:

---

Method 1: Using a Custom Style Extension

Compatible with Chrome, Firefox, and Edge.

1. Install a User Style Manager Extension:

   • Chrome/Edge: Stylus
   • Firefox: Stylus for Firefox

2. Create a New Style for Gmail:

   • Click on the Stylus extension icon in your browser toolbar.
   • Select "Manage" or "Write new style."
   • Set the style to apply to URLs matching mail.google.com.

3. Add Custom CSS to Hide the Button:

   /* Hides the "Summarize this email" button */
   div[aria-label="Summarize this email"] {
       display: none !important;
   }
   

4. Save and Apply the Style:

   • Click "Save" to apply the changes.
   • Refresh your Gmail tab to see the effect.

---

Method 2: Using an Ad Blocker Extension

If you already use an ad blocker like uBlock Origin.

1. Access uBlock Origin's Dashboard:

   • Click the uBlock Origin icon in your browser.
   • Click the "Settings" (gear) icon to open the dashboard.

2. Add a Custom Filter:

   • Navigate to the "My filters" tab.

   • Insert the following filter rule:

     mail.google.com###:xpath(//div[@aria-label='Summarize this email'])
     

3. Apply the Changes:

   • Click "Apply changes."
   • Refresh Gmail to remove the button.

---

Notes:

• Maintenance: These solutions rely on Gmail's current HTML structure. If Gmail updates its interface, you may need to adjust the CSS selector or filter accordingly.
• Security: Be cautious when using extensions and ensure they are from reputable sources to protect your account information.
• Feedback to Google: If this feature disrupts your user experience, consider sending feedback to Google:
  • In Gmail, click the "Settings" gear icon.
  • Select "Help & feedback," then "Send feedback to Google."

---

By using these methods, you can customize your Gmail interface to better suit your preferences until an official option becomes available.

Answer on Accounting for deletions in recurring meetings that "repeat for N times"

Google Calendar doesn't automatically adjust the number of occurrences in a recurring event series when individual events are deleted. When you set an event to "repeat N times," it schedules N occurrences regardless of any deletions you make afterward. This can indeed make tracking the actual number of remaining sessions challenging, especially in cases like yours where classes must meet a specific number of times.

However, there are a few workarounds you can use to manage this more effectively:

---

Option 1: Modify Events Instead of Deleting

Instead of deleting canceled sessions, you can modify them to indicate they're canceled. This way, the total count of occurrences remains accurate, and you can visually distinguish between active and canceled sessions.

1. Edit the Individual Event:

   • Click on the event occurrence you want to cancel.
   • Choose "Edit event" (not "Delete").
   • Modify the event title to include "[Canceled]" or change the event color to a distinct one for cancellations.
   • Save the changes only for this event.

2. Benefits:

   • The total number of scheduled sessions remains unchanged.
   • You retain a record of all planned sessions, canceled or not.
   • Visual indicators help you track which sessions are canceled.

---

Option 2: Use the "Repeat Until" Feature with Buffer

Set your recurring event to end on a specific date that goes beyond your expected end date, accounting for possible cancellations.

1. Create the Recurring Event:

   • Set the event to repeat on the desired days.
   • Use the "Ends on" option to select a date well past the expected completion date (e.g., a few weeks later to account for possible cancellations).

2. Manually Track Completed Sessions:

   • Keep a simple tally of completed sessions.
   • Once you've reached the required number of sessions (e.g., 25), you can end the series.

3. Benefits:

   • No need to adjust the number of occurrences after each cancellation.
   • Flexibility to accommodate an indefinite number of cancellations.

---

Option 3: Utilize Google Sheets with Apps Script to Count Sessions

Automate the tracking of your sessions using Google Sheets and Apps Script. This method allows you to count the number of remaining, completed, and canceled sessions.

1. Set Up a Google Sheet:

   • Create a new Google Sheet to serve as your tracking dashboard.

2. Access Apps Script:

   • In the Google Sheet, go to Extensions > Apps Script.

3. Insert the Following Script:

   function countSessions() {
     var calendarId = 'primary'; // Replace with your calendar ID if not using the primary calendar
     var eventTitle = 'TEST'; // Replace with your event title
     var totalRequiredSessions = 25; // Your target number of sessions
   
     var calendar = CalendarApp.getCalendarById(calendarId);
     var now = new Date();
     var future = new Date();
     future.setFullYear(future.getFullYear() + 1); // Adjust as necessary
   
     var events = calendar.getEvents(now, future, { search: eventTitle });
     var completed = 0;
     var remaining = 0;
     var canceled = 0;
   
     events.forEach(function(event) {
       var title = event.getTitle();
       if (title.includes(eventTitle)) {
         if (title.toLowerCase().includes('canceled')) {
           canceled++;
         } else if (event.getEndTime() < now) {
           completed++;
         } else {
           remaining++;
         }
       }
     });
   
     var totalScheduled = completed + remaining;
   
     var sheet = SpreadsheetApp.getActiveSpreadsheet().getActiveSheet();
     sheet.getRange('A1').setValue('Total Required Sessions');
     sheet.getRange('B1').setValue(totalRequiredSessions);
     sheet.getRange('A2').setValue('Completed Sessions');
     sheet.getRange('B2').setValue(completed);
     sheet.getRange('A3').setValue('Remaining Sessions');
     sheet.getRange('B3').setValue(remaining);
     sheet.getRange('A4').setValue('Canceled Sessions');
     sheet.getRange('B4').setValue(canceled);
     sheet.getRange('A5').setValue('Total Scheduled Sessions');
     sheet.getRange('B5').setValue(totalScheduled);
   }
   

4. Run the Script:

   • Save the script and click the Run button (you'll need to authorize the script to access your calendar).
   • The counts will populate in your Google Sheet.

5. Set Up a Trigger (Optional):

   • Automate the script to run daily by setting up a trigger in Apps Script > Triggers.

6. Benefits:

   • Automated tracking of your sessions.
   • Clear visibility into how many sessions are completed, remaining, or canceled.
   • Reduces manual counting errors.

---

Option 4: Use a Third-Party Scheduling Tool

Consider using specialized scheduling software that offers more advanced features for recurring events and session tracking.

• Features to Look For:

  • Ability to set a fixed number of occurrences that adjust based on cancellations.
  • Advanced reporting and tracking of sessions.
  • Integration with Google Calendar to keep everything synchronized.

• Popular Tools:

  • Acuity Scheduling
  • Calendly
  • Setmore

• Benefits:

  • Streamlined management of recurring sessions.
  • Automated adjustments for cancellations.
  • Additional features like client notifications and attendance tracking.

---

Conclusion

While Google Calendar doesn't automatically adjust recurring event counts based on deletions, these workarounds can help you manage your class sessions more effectively. By modifying events instead of deleting them, utilizing Google Sheets and Apps Script for tracking, or adopting a third-party tool, you can reduce errors and ensure you meet your required number of class sessions without the hassle of manual counting.

There was also an answer on How can I remove labels from Google Maps when looking at the terrain option?, but it appears to have been deleted and isn't visible to me.

Answer 3

As a direct reply to the answer by Philippe:

Thanks for the clarification. It becomes clear that the bot was not yet ready for publication and therefore we cannot assume that this is the final version of it. We will need to wait and see how it really looks in the end.

In the meantime, maybe a little reminder of your words from February 2024:

Attribution is non-negotiable

All products based on models that consume public Stack Overflow data are required to provide attribution back to the highest relevance posts that influenced the summary given by the model. With the lack of trust being felt in AI-generated content, it is critical to give credit to the author/subject matter expert and the larger community who created and curated the content being shared by an LLM. This also ensures LLMs use the most relevant and up-to-date information and content, ultimately presenting the Rosetta Stone needed by a model to build trust in sources and resulting decisions. Sharing credit ties to attribution and with attribution—trust is at the heart.

Unless this was all just idle talk (which it might well have been), I would expect this new product (if it's based on consuming Stack Overflow data or other similarly licensed data) to give full credit to all authors/subject matter experts contributing to the output as required by the licenses of all contributions from Stack Overflow or also elsewhere.

I don't think it does so currently (doesn't look like it) and I don't think there is nearly enough time until say January next year to fix that, but you used big words ("trust is at the heart") and it would look relatively bad if at the end it was just an empty promise. Trust might be gone at that point.

Looking forward to seeing lots of attributions.

Answer 4

This answer is response to official answer posted by Philippe

This experiment takes a long view. We're in the early learning stages and will be working with a handful of sites to understand potential value.

There is zero value in having AI generated answers on any site. Anyone who wishes to use AI can go and easily ask AI. Posting question on any site in SE network requires more preparation and work than merely asking AI.

People who come to the SE want to have their answers written by experts who actually know what they are talking about, not AI. Nowadays, many are coming here only after they have already unsuccessfully tried to ask AI and got nothing usable.

We won’t know whether or not those are viable without experimentation.

Except we do know. And we told you that. Moderators, especially Stack Overflow ones, have seen and have removed thousands of AI posts. Most of those were utmost crap. For the same reason why we don't allow users to post AI, this experiment will also fail. The results will be just load of junk containing potentially dangerous and harmful information.

While there is a certain value in experimenting, gathering the results and making further decisions based on those, not literally every idea need to end up as an experiment. No amount of experimenting will make bad idea a good one. And "Answer Assistant" is one of most horrible ideas ever.

The experiment is designed to be configurable on a per-site basis to align with the dynamics, policies, and goals of specific communities.

There is very little to configure here. There are no configurations and tweaking that would possible make this feature tolerable in any way on the sites that don't want it. Sites will either have "Answer Assistant" or not.

And we already know from the experience that you will find all kinds of reasons for pushing the feature on sites regardless of its community wishes.

We will explore designs, methods of human vetting and editing of LLM-originated content, and the scenarios where this might provide value.

Who do you think will vet AI content?

Users who have no clue whether AI provided information is correct or not.

People who can verify the correctness of AI answers are capable of writing their own answers. Why would they waste their time verifying AI?

Already we see many examples of SE contributors utilizing LLM resources, and the added workload on moderators and curators that this creates.

I will repeat my comment here: Are you seriously going to use that as an excuse? Moderators are fully capable of handling and removing LLM content posted by users. It was the company that literally prevented moderators from doing so which lead to the last years strike. Almost all problems and extreme workload for moderators were caused by company's actions. Please don't try to sell this feature, which was strongly opposed by moderators, as something that will help us. It will not.

This experiment is about preparing for the future.

A very bleak future. You can be a beacon of human light in the world flooded with AI, yet your choice is vanishing into the darkness.