Artificial Intelligence Study Group
|
Contacts: jdberleant@ualr.edu and mgmilanova@ualr.edu
Agenda & Minutes (176th meeting, Aug. 29, 2025)
Table of Contents
* Agenda and minutes
* Appendix: Transcript (when available)
Agenda and Minutes
- Announcements, updates, questions, etc.
- MM pointed out the table of AI resources at https://ai.nd.edu/ai-in-action/approved-ai-tools/.
- "Join us for a thought-provoking lecture and book signing with renowned economist and King’s College London professor Daniel Susskind as part of the CBHHS Research Symposium."
Thursday, September 4, 2:00 p.m., UA Little Rock, University Theatre – Campus conversation
Friday, September 5, 2:00 p.m., UA Little Rock, University Theatre – Campus and community conversation
Susskind, a leading voice on the future of work and technology, will explore how artificial intelligence is reshaping the workplace and how we can harness its potential to work smarter. Don’t miss this opportunity to engage with one of today’s most influential thinkers on AI, economics, and the future of our professions.
- Sept. 12: ES will tell us about The AI-Driven Leader: Harnessing AI to Make Faster, Smarter Decisions, by Geoff Woods. Please help discuss it, ask questions, etc.!
- Here are projects that MS students can sign up for. If anyone has an idea for an MS project where the student reports to us for a few minutes each week for discussion and feedback - a student might potentially be recruited! Let me know.
- Book writing project
- 8/22/2025: LG has signed up for this. Next time will try both and report back, and also start the log of the project.
- Working on how to write the book. Have different agents doing different roles?
- Topic of book will be: personal investing
- Committee: DB, MM, RS; Y is welcome to apply for AGFS and then be on the committee.
- Does the Donaghey Scholars program have guidelines on report structure? IU suggests LG could contact Dr. S. Hawkins and/or Dr. J. Scott, who are involved in the program, to see if they have any such guidelines.
- VW had some specific AI-related topics that need books about them.
- JH suggests a project in which AI is used to help students adjust their resumes to match key terms in job descriptions, to help their resumes bubble to the top when the many resumes are screened early in the hiring process.
- JC suggested: social media are using AI to decide what to present to them, the notorious "algorithms." Suggestion: a social media cockpit from which users can say what sorts of things they want. Screen scrape the user's feeds from social media outputs to find the right stuff. Might overlap with COSMOS. Project could be adapted to either tech-savvy CS or application-oriented IS or IQ students.
- DD suggests having a student do something related to Mark Windsor's presentation. He might like to be involved, but this would not be absolutely necessary.
- markwindsorr@atlas-research.io writes on 7/14/2025:
Our research PDF processing and text-to-notebook workflows are now in beta and ready for you to try.
You can now:
- Upload research papers (PDF) or paste in an arXiv link and get executable notebooks
- Generate notebook workflows from text prompts
- Run everything directly in our shared Jupyter environment
This is an early beta, so expect some rough edges - but we're excited to get your feedback on what's working and what needs improvement.
Best, Mark
P.S. Found a bug or have suggestions? Hit reply - we read every response during beta.
Log In Here: https://atlas-research.io - AI course updates? About 15 students currently, to be organized into teams. There will be projects due at the end of the semester.
- EG suggests students might benechecking out rapids.ai.
- Any questions you'd like to bring up for discussion, just let me know.
- Anyone read an article recently they can tell us about next time?
- Any other updates or announcements?
- Here is the latest on future readings and viewings. Let me know of anything you'd like to have us evaluate for a fuller reading, viewing or discussion.
- Evaluated
- 7/25/25: eval was 4.5 (over 4 people). https://transformer-circuits.pub/2025/attribution-graphs/biology.html.
- https://arxiv.org/pdf/2001.08361. 5/30/25: eval was 4. 7/25/25: vote was 2.5.
- We can evaluate https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10718663 for reading & discussion. 7/25/25: vote was 3.25 over 4 people.
- Evaluation was 4.4 (6 people) on 8/8/25: https://transformer-circuits.pub/2025/attribution-graphs/biology.html#dives-refusals
- Evaluation was 3.87 on 8/8/25 (6 people voted): https://venturebeat.com/ai/anthropic-flips-the-script-on-ai-in-education-claude-learning-mode-makes-students-do-the-thinking
- Evaluation was 3.5 by 6 people on 8/8/25: Put the following into an AI and interact - ask it to summarize, etc.
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning (https://transformer-circuits.pub/2023/monosemantic-features/index.html); Bricken, T., et al., 2023. Transformer Circuits Thread.
- Evaluation was 3.75 by 6 people on 8/8/25 for: Use the same process as above but on another article.
- 8/22/25: eval. was 4.0 (4 people): Https://www.nobelprize.org/uploads/2024/10/popular-physicsprize2024-2.pdf.
- (Eval 8/29/25 was 3.75 over 5 people.) Https://docs.google.com/document/d/1NeNmKlAmJdf50ST7plw4mvgeeS7UJuYLyEQMz8slCA0/edit?tab=t.0#heading=h.hnzmulgvk3qx.
- Prompt engineering course.
- Also at Syllabus page: https://apps.cognitiveclass.ai/learning/course/course-v1:IBMSkillsNetwork+AI0117EN+v1/home.
- Registration page: https://apps.cognitiveclass.ai/learning/course/course-v1:IBMSkillsNetwork+AI0117EN+v1/home
- Requires registering. DD volunteered to register if it is free, so we can check it out briefly and decide if to do the course in detail.
- Not yet evaluated
- Neural Networks, Deep Learning: The basics of neural networks, and the math behind how they learn, https://www.3blue1brown.com/topics/neural-networks. (We would need to pick a specific one later.)
- We checked the first one briefly. 8/22/25: eval was 3.625 (from 4 people) for a full viewing.
- Let's evaluate a few more of them.
- LangChain free tutorial, https://www.youtube.com/@LangChain/videos. (The evaluation question is, do we investigate this any further?)
- Chapter 6 recommends material by Andrej Karpathy, https://www.youtube.com/@AndrejKarpathy/videos for learning more. What is the evaluation question? "Someone should check into these and suggest something more specific"?
- Chapter 6 recommends material by Chris Olah, https://www.youtube.com/results?search_query=chris+olah
- Chapter 6 recommended https://www.youtube.com/c/VCubingX for relevant material, in particular https://www.youtube.com/watch?v=1il-s4mgNdI
- Chapter 6 recommended Art of the Problem, in particular https://www.youtube.com/watch?v=OFS90-FX6pg
- LLMs and the singularity: https://philpapers.org/go.pl?id=ISHLLM&u=https%3A%2F%2Fphilpapers.org%2Farchive%2FISHLLM.pdf (summarized at: https://poe.com/s/WuYyhuciNwlFuSR0SVEt). (Old eval from 6/7/24 was 4 3/7.)
- Back burner "when possible" items:
- TE is in the informal campus faculty AI discussion group.
- SL: "I've been asked to lead the DCSTEM College AI Ad Hoc Committee. ... We’ll discuss AI’s role in our curriculum, how to integrate AI literacy into courses, and strategies for guiding students on responsible AI use."
- Anyone read an article recently they can tell us about?
- The campus has assigned a group to participate in the AAC&U AI Institute's activity "AI Pedagogy in the Curriculum." IU is on it and may be able to provide updates now and then.
Appendix: TranscriptArtificial Intelligence Study Group
Fri, Aug 29, 2025
0:18 - R. S.
you you Yeah.
2:20 - M. M.
Hi, D. and D. and R. I know it's busy time, so this is why we're not having more people because right now it's really start the semester. But I sent to D. some links and I want to send right now another link. How do universities generative AI. So I'm copy right now. Are you bringing in the chat?
2:56 - D. B.
Yes, I will.
2:57 - M. M.
Because I told you they will have a lot of discussions right now. What kind of tools to use it, how to use it. So this is one. That I received today. They are internet discussions. I'm not participating in our university discussions, but this is from outside, from North Dam University. And I think that they have a very good table if you go to the table. Oh, I can share. Yeah, do you want to share your screen?
3:46 - D. B.
Yeah, you're showing, but go to the table.
3:50 - M. M.
You show.
3:51 - D. B.
All right, am I still showing it?
3:55 - M. M.
No, no, but it was there. All right.
4:06 - M. M.
I wish that our university, I'm not aware if our university prepares something like this, but they have a table. Can you go down and...
4:21 - D. B.
Yeah. Yeah. I don't see the table. Maybe in the resources. Go to resources. There's a good table.
4:31 - M. M.
Yeah. Yeah. I don't know, more event tables about the price and how they can use it and all the tools are listed. I don't know, maybe I can share.
4:50 - D. B.
Yeah, sure, you have it?
4:56 - M. M.
It's not coming to you. Oh. Hold on.
5:05 - Unidentified Speaker
It was here for me.
5:10 - M. M.
Oh, why is it not coming now? But several, University of Arizona, another one also. Yes.
5:30 - Unidentified Speaker
It's not coming though.
5:31 - D. B.
There should be a green share screen icon.
5:39 - M. M.
No, I know, but I am not finding the table. The table is under AI in action and then approved tools.
5:49 - L. G.
They have a table that lists all the tools that they use there. I think maybe that's what you're looking for. I'm not sure.
6:00 - M. M.
Yeah, yeah. Yeah, yeah, yeah, you're correct, yes. Yes, yes, okay, I can share. Yeah, so, but I wish that... Is this one? I'm not sure that I'm correct. No, it's not this one. Maybe. Can you see it now? Yeah, yeah, so I wish that our people create the table like this. What is free? Cloud free some small subscription notebook is free. So yeah. Yeah, but but there are many universities I receive from University of from another one, several. I'm not aware that our university creates the resources for our students, but they are probably working on this.
7:11 - D. B.
So how did you get that table? Did you go to resources? Approve AI tools Oh, I see, approved AI tools.
7:28 - M. M.
And they have a lot of... So we will have this D. person talking this week, coming, I think, about the AI in education in our university.
7:49 - D. B.
Yeah, OK, so let me just catch up with.
8:03 - M. M.
Yeah. Yes, exactly. You can list the The web page.
8:18 - D. B.
Yeah, I got it. OK, so yeah, there's going to be a seminar. This guy from London is going to be talking about AI next Thursday, next Friday at 2 PM each time in the University Theater. And they want you to Thursday is the campus conversation. Friday is the campus and community So anyway, if anyone, I might try to get, try to go to it. If anyone else does, we can, you know, talk about it a bit at the meeting, at our meeting. This guy is, works in the future of work in technology and they want you to register to attend, but I don't think it's, I mean, I think probably you want to know how many people go, but they're not going to turn you away from the university theater. Yeah, there is a space.
9:16 - Unidentified Speaker
if you don't register, it's okay.
9:19 - D. B.
And then on September 12th, E. S. in the psychology department is going to be a guest here and is going to tell us about a book I group Read over the summer called this. And so I hope people will feel free to, you know, ask, you know, help her, help her out a little bit. Don't just like, listen to her and then say, thanks, just try to ask some questions and so on. Because it's pretty, you know, these presentations we have are all generally pretty informal.
9:57 - M. M.
So, you know, the guests need to be encouraged. Yeah.
10:03 - D. B.
So we got a book writing project. So L. is working on that. And I want you to know. L., do you want to tell us how it's going? And do you have any questions or anything, insights or questions?
10:34 - L. G.
Yeah, well, I don't have any questions. Questions this week. It's been kind of a rough week. I spent a little time trying to set up both of the tools I wanted to use. It's taken a little bit longer than I've been able to do yet, so I'm a little bit behind on it, but hopefully I have more questions and some answers and more next week. Okay.
10:58 - D. B.
Well, if you've been checking two tools and so on, that's definitely something we want to see in the log, the report that will become your report. Any observations you have about them? Yes, sir.
11:12 - L. G.
In that case, I have a lot of observations right now about getting them set up well. So I include that in the report as well.
11:25 - Unidentified Speaker
OK, sounds good.
11:26 - D. B.
R. and F., do you have any other guidance for L. since you're on the committee? Not right now. All right, let's go to... Okay, so we're still evaluating different readings and so on. I don't know when to stop even and start doing one of them for real, but now we could have a few more here. We don't have a lot of people here today, so might as well do that. Let's go to here and see how this one is. Okay, 10 predictions for 2025.
12:37 - Unidentified Speaker
This is a December 2025 article. This could be a problem.
12:51 - D. B.
Okay, well, I'm going to kick that one out because I don't have permission to view it and I don't want to be fighting with this thing all the time.
13:07 - Unidentified Speaker
So I'm going to just get rid of this one.
13:13 - D. B.
Let's go on to this one. You OK, so this is a course that I think D. was offering to potentially share his screen if he wanted to go through this course. But for today, we'll just view the syllabus and see what we think.
14:05 - Unidentified Speaker
So let's take a look from here. Let's start from those.
14:11 - D. B.
So Read that, and we'll see if there's comments about it? Lots of comments? All right, let's go on to the next paragraph.
14:34 - M. M.
Yeah, I just want to mention that Prompt engineering is really very important because it's integrated and it's a big part of agentic AI. So they go together, you know?
14:54 - Unidentified Speaker
Yeah, I think prompt engineering is interesting, is of interest to anyone, whether they're tech folks or not.
15:03 - Unidentified Speaker
Exactly.
15:04 - M. M.
Or yeah, for anybody, you know, if you are users or if they are developers.
15:11 - D. B.
Yeah, I mean, you could you could almost, you know, start.
15:15 - D.
You could you could almost start researching prompting engineering at this time and and do and do tests and see, you know. If you were to prompt this way, this is the results that you get if you were to this way, this is the different results. I mean, there's there's this is open terrain.
15:39 - M. M.
Yeah, I think there's a lot of research that could be done.
15:44 - D. B.
One issue, though, is how these things respond to prompts could change on a week-to-week basis. So research could get out of date pretty quickly. But that doesn't mean it's not important.
15:58 - D.
Well, maybe. I guess it really depends on where you're chatting with it. So in the chat, like your open chat that you just go to the chat site. But if you're in the API, especially like in chat GPT, and I think in some of the other models, it's kind of locked so that you can do research.
16:23 - D. B.
Yeah, but I mean, even if you're accessing it through the API, how the system responds to the API changes.
16:31 - D.
It's not that stable, right? OK, so you've got a good point that depending on the temperature and the top we talked about, you know, that could cause you to get kind of, maybe not random, but more random responses, right? So, but you know, there's ways to pin it down and find out the bottom line if you bring that top and that temperature down.
17:00 - D. B.
Another thing I wonder is if there's, are there general principles of prompt engineering that can be expected to apply long term? I'd say, well, they're going to change how they respond to prompts from week to week and blah, blah, depending on the news cycle and what happens in the marketplace. But are there general principles of prompt engineering that are going to stay constant? And if so, what are they?
17:30 - D.
That's a really good point. That's right. If so, is there patterns to the change? Yeah. There's a lot. I mean, it's really open terrain to anybody who really wants to do some research on it. It's open.
17:54 - D. B.
All right. Well, let's Read this next chunk here. About that.
18:07 - Unidentified Speaker
Any comments? Any comments?
18:26 - D.
Well, I Read all this already. Yeah.
18:30 - D. B.
Limitations of naive prompting. Cause that's, you know, you don't learn prompting, I guess what you, you know, if you don't learn formally how to prompt, I guess you're limited. You're, you're, you're there with naive prompting. So what am I doing wrong?
18:46 - D.
I took, I took a course and then I changed. I changed the way I prompt. It's like a Udemy course. And then I started looking at V.'s prompts and then I changed my prompts again. And now I'm kind of back to where I was kind of when I started. So my promptings then went full circle. So I'd like to know what other people think and what they're using and what they found.
19:23 - D. B.
V.'s prompts were a little more wordy than they needed to be. And, and I'm not sure like he was, he would tell the AI, you know, you are a world expert. Well, does that change how it responds compared if you don't say that?
19:40 - D.
So it seems like to me that from my experience that I did not get any, you know, higher quality results, you know, like if I did, tell it what's going on, what I'm doing, I get better results. If there's context, so context seems to be very important. It's probably maybe the most important thing. Because if I just tell the AI what I want, it could be interpreted many different ways. That the AI is going to think, well, he wants this for this or he wants this for that. And so if I context but no I'm you know telling the ai that it's hot sauce doesn't seem to really change anything that I can tell but V. gets some really good results man he really does i've been playing around with uh including a thing at the end of some and ask me questions if you, you know, if you need some, you know, additional information.
20:49 - L. G.
And I found that to be helpful in, helpful in providing clear instructions in a way. Yeah, I mean, so, but it does come back and say.
21:00 - Unidentified Speaker
Oh, yeah.
21:00 - L. G.
Oh, yeah. Yeah. Hold on, let me, maybe I can look at what I did at work. Hold on, we'll check it out. Look for, give me one moment.
21:12 - D. B.
Sure.
21:13 - L. G.
So at work, I was trying to figure out the best way to do a spreadsheet for someone. And what we found out is I asked it at the end. So I guess if I can find it. All right. What I asked it was, I said, I'm working as a financial analyst. I am building a workbook where we receive a large data set on one worksheet, and you use it on other worksheets. On a second worksheet, I would like to gather transactions that are row-based on the date and present them into two sets based on the amount column. One area for positive values, one area for negative values. And zero values would not be included. What are some of the ways that we could do this in Excel or Python? Please ask additional questions if needed. And yeah, it asked questions. It said, is the incoming data always set, always structured? Do you want the output on the second worksheet to update automatically when new data is pasted into the first worksheet and gave some examples of what it was saying. And it's a filtered list of full transactions where I needed to exclude some columns or fields.
22:44 - Unidentified Speaker
Yeah.
22:45 - D. B.
Interesting.
22:45 - D.
That's pretty good questions, too, because a lot of times I've noticed that the AI makes assumptions on how I want stuff, and it can get frustrating after a while when hey, I'm going to start doing that. Yeah.
23:01 - Unidentified Speaker
That's what led me down that path, because I would get, it would answer a question it thought I asked, but it wasn't the question I was asking. So then I, that's why I started adding that line.
23:12 - D. B.
I mean, you can, you can try to fix your, you know, if you see it's misunderstanding, you can, you can try to correct it mid-course, but why, why, why not ask it to correct it, you know, to ask you what it needs to know. That sounds more efficient.
23:28 - D.
It does. Yeah. So I would like to know what model you're using. For that one, I was using just simple, it looks like,
23:37 - L. G.
Hold on, I have to make it bigger. I was using check GPT. I don't know which model right now. Check GPT, it's probably five. You're using it on the front end.
23:50 - D.
I think it's five. Yeah, I think just the right one.
23:54 - Unidentified Speaker
Yeah, you're probably using it.
23:56 - D.
Five's what they're putting on their face right now, so.
23:59 - L. G.
Okay, then that's, yeah, I just did it like a couple of days ago.
24:03 - D.
Okay, thank you.
24:22 - Unidentified Speaker
Oops.
24:23 - D. B.
All right.
24:34 - Unidentified Speaker
OK, there's another chunk to me. Any comments? Just to me, this looks like really practical and valuable and practical sample.
25:03 - D.
Yeah, I mean, you know, it would be interesting just to kind of, you know, skim through this and see what... We could even try some of these exercises as we go along. You know, each person's on a computer, they can...
25:18 - Unidentified Speaker
I only get one grade now.
25:20 - D.
Or, you know, whoever's sharing their screen can try it and you can all see what's going on.
25:26 - D. B.
The only thing I remember is that you only get graded for the first is what? You only get graded for the first time.
25:36 - D.
Who's being graded? At IBM, they're going to grade it and it'll be on my certificate. So if we mess up, that's it.
25:44 - D. B.
My name is tarnished for life. Uh-oh. No.
25:47 - D.
I might want to rush through it real quick and do my best before we mess it up.
25:53 - D. B.
If we do it together, can we get a certificate saying, you know, AI discussion group has passed I mean, we would have to probably set up a Google account for, you know, like an email.
26:06 - D.
We need an AI discussion group email, but right now it's under my name.
26:11 - D. B.
Okay, well, I'll do my best to make you look good then.
26:15 - D.
All right. Might think I'm just some kind of scrub or something.
26:20 - Unidentified Speaker
You know, maybe if you ever thought of applying for a job at IBM, maybe we should pick somebody else to Just make sure we'll just make sure V.'s here.
26:42 - Unidentified Speaker
All right, next chunk here. Any comments?
26:56 - Unidentified Speaker
OK. And that is it. It's time to vote.
27:00 - Unidentified Speaker
You guys are saying that there's the NOVA system and the Watts-Knox-Prompt lab and... Watson X? Yeah. I said Watson X.
27:09 - D. B.
Is that how they would say that?
27:12 - D.
Well, I mean, they have the Watson, which will beat the chess champion.
27:21 - D.
I mean, I think it'd be interesting.
27:24 - Unidentified Speaker
I like that name Watson.
27:25 - D.
If we, if we start going through it and we think that it's just, you know, not really, you know, there's no real thought in it.
27:33 - Unidentified Speaker
Just some basic surface level stuff. We could stop doing it.
27:37 - D. B.
That's true for any of our readings. You know, I don't know that we do it very often, but if we don't like a reading, we can quit anytime. Absolutely true. All right, well, let's go ahead to, to the evaluation.
27:53 - Unidentified Speaker
So again, type into the chat or tell me your answer.
27:59 - D. B.
So one would be definitely don't want to do this. Five, you definitely do. Three, meaning either way.
28:10 - Unidentified Speaker
And two and four are in-betweens. Okay.
28:15 - R. S.
How long is this course if we follow?
28:18 - M. M.
You know what?
28:19 - D.
I've been trying to log back into it. I'm on my laptop, and I did that on my desktop at home. So I haven't been able to get back into it. But it seems like it's, you know, seemed like it was kind of long. Well, it's not like that. You know, for this context, I don't know. I can find out and, you know, definitely before we start anything we'll know. There's a link in the minutes, right?
28:54 - D. B.
That's how I got there. Yeah. Let me go back to the minutes. If it's something short, it's fine.
29:05 - M. M.
No, it's not short. It's a course.
29:08 - D.
No? No, I'm pretty sure it's not. Well, I mean, I don't mean like that. They have multiple labs, right?
29:19 - D. B.
Clearly, each lab is one session.
29:22 - M. M.
And how many links are to the There it is. That's the link that says minutes in it.
29:33 - Unidentified Speaker
Let me type in IBM.
30:04 - D.
I signed up when I was scoring.
30:12 - Unidentified Speaker
All right, 3.75.
30:15 - D. B.
3.75 is the evaluation.
30:34 - Unidentified Speaker
3.75? Yeah.
30:43 - D. B.
It's not super hot.
30:46 - D.
OK, so this one, so maybe I use my school email. I'm going to be safe.
30:53 - Unidentified Speaker
Let me go to the, go here and see. I don't know. Is it this one?
31:02 - D. B.
I don't remember what we were looking at. I mean, I've got the right thing.
31:09 - D.
I recognize the number. I'm just trying to get in.
31:14 - Unidentified Speaker
Yeah. So I did it. Okay. I did it.
31:18 - D.
Uh, the first module, everything says it's a minute long. One minute. Yeah.
31:25 - D. B.
I mean, it's, it just says, Oh, it says one activity.
31:30 - D.
Okay.
31:34 - Unidentified Speaker
about this course. It says casual one day a week. Yeah, I mean, I think at some point it told me, but I may not be able to find out how long it is. But there's five modules. And the first module is like five minutes.
32:13 - D.
The second module has a five question quiz in a couple of minutes. But the second module has four activities. It doesn't say time this goes into activity that maybe it's pretty quick it might be pretty quick it looks like it it's gonna be very quick thing maybe I got that I got confused when it's a casual one day a week this might be something we can knock out and like one session two or something you know how hard can it be How much time can it take to learn a prompt method? If you want, I'll share my screen and show you what I'm looking at.
33:12 - D. B.
Yeah, sure.
33:15 - D. B.
You guys see that?
33:38 - Unidentified Speaker
You guys are seeing this right? Anybody?
33:42 - D. B.
People seeing it? Yes. It's just like five modules.
33:50 - M. M.
It doesn't look like it's that much.
33:55 - D.
No, it's not. It's a pretty short little thing.
34:00 - M. M.
Well, anyone want to change their votes?
34:08 - D. B.
OK. I think we lost L.
34:12 - Unidentified Speaker
Is that his name? L.?
34:15 - D. B.
Is he gone? We lost L. All right.
34:32 - D.
He was definitely not interested in it, it looked like, No, he wasn't.
34:39 - Unidentified Speaker
He's got his own prompting methods now. Wasn't it kind of light last week too?
34:51 - D. B.
Yeah, it's been light for a couple of weeks.
34:57 - D.
It's kind of hard time for everybody. Yes.
35:03 - Unidentified Speaker
I haven't seen V. This is like three weeks in a row. He does not want to do the wind tunnel.
35:11 - D.
I mean, it is clear at this point. I'm going to have to tell him he's off the hook so he'll come back.
35:25 - Unidentified Speaker
Well, what else?
35:28 - D. B.
All this stuff is based, a bunch of stuff based on what we, those series of videos that we talked about. You want to look at another one? Evaluated something else or do we want to end now?
35:59 - D.
If we start getting a bunch of people and just a few of us make that decision, it might be kind of rough.
36:12 - D. B.
Yeah, there's not really, there's only four of us. All right, well, let's have a short meeting today. And we'll hopefully get more people next time. And if we don't, I mean, the important thing is that it's a valuable meeting. If the meetings start to get not so valuable, then it's a time to either do a recruitment drive or move on to other things.
36:41 - D.
Well, it could be that they have jobs that require them to be worked till five or something. Because luckily, I get off that I can be here for as long as I stay at work. I don't know.
36:57 - Unidentified Speaker
I mean, we've had other people here before. It used to be, last semester we had 10, 11 people every time.
37:05 - M. M.
Yeah.
37:05 - Unidentified Speaker
Yeah.
37:05 - D.
It was really good. But it's, you know, like Dr. M. said, it's the first part of the semester. Yeah.
37:14 - D. B.
I could send out a calendar reminder saying, hey, you know, Remember, we're doing it. Come back. That would be good.
37:22 - D.
Nice recruitment, yes.
37:24 - M. M.
We need to do some more advertisement. Yeah. All right, folks.
37:28 - D. B.
Well, thanks for joining in, and we'll see you next time.
37:32 - D.
All right. Bye, guys.
