Welcome to DU!
The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards.
Join the community:
Create a free account
Support DU (and get rid of ads!):
Become a Star Member
Latest Breaking News
Editorials & Other Articles
General Discussion
The DU Lounge
All Forums
Issue Forums
Culture Forums
Alliance Forums
Region Forums
Support Forums
Help & Search
As someone who must use AI daily for coding for work, when people try to convince me that AI can't "think"? [View all]
I have to shake my head a bit 
Because if you use it regularly, you know AI is absolutely capable of fairly complex logical thinking. And honestly, Gemini figuring out what I was asking it below was *child's play* compared to what I've seen it do in other situations. This was a very easy question.
Also, this was just Gemini 3.1 Flash Preview, not even the 3.1 Pro Preview ("Flash" is the cheaper, less deep-thinking version vs "Pro" ).
Check out my prompt below, and its reply. Here, I'm describing how our company's yearly retainer "projects" (which have a fixed number of hours for a year we can bill to the client) are divvied up into specific tasks (like 'coding' vs 'planning' or the like) , and then each task has an 'estimated hours' assigned for each of the next 12 months. I told it I want to build a graph for every project that looks at how many hours have been billed as 'worked' by employees across all tasks in the retainer, plus another metric that will make that particular metric useful to managers. But I did not tell AI what that metric was, I challenged it.
Me:
Now I'm going to challenge you a little bit to figure something out. A retainer PROJECT is
generally 1 year, with some number of quoted hours. These projects generally have a collection of 1-4
purpose-driven tasks (typically there are 2, and they are "Implementation and Testing" and "Planning and
Communication", but that doesn't HAVE to be the case, but what we DO always do is estimate all the quoted hours out
into task-based estimate records over the course of the year), with the same start and end dates as the project.
Then, we have monthly estimates per task, which LOOSELY will be about 75% of hours into I&T, and 25% into P&C, and
the total quoted hours are split across the 12 months, with small adjustments based on 'work days per month' as I
mentioned in my very first post. Whatever the math is there should be a black box to you, the important point is
we'll have estimates for each month of each task under each retainer project. Therefore, looking purely at % of
quoted hours used (as of today) is basically meaningless. There's one more, very basic metric we need to make "how many
hours have we burned" into a MEANINGFUL statistic. What do imagine that metric might be?
generally 1 year, with some number of quoted hours. These projects generally have a collection of 1-4
purpose-driven tasks (typically there are 2, and they are "Implementation and Testing" and "Planning and
Communication", but that doesn't HAVE to be the case, but what we DO always do is estimate all the quoted hours out
into task-based estimate records over the course of the year), with the same start and end dates as the project.
Then, we have monthly estimates per task, which LOOSELY will be about 75% of hours into I&T, and 25% into P&C, and
the total quoted hours are split across the 12 months, with small adjustments based on 'work days per month' as I
mentioned in my very first post. Whatever the math is there should be a black box to you, the important point is
we'll have estimates for each month of each task under each retainer project. Therefore, looking purely at % of
quoted hours used (as of today) is basically meaningless. There's one more, very basic metric we need to make "how many
hours have we burned" into a MEANINGFUL statistic. What do imagine that metric might be?
AI Reply:
✦ Based on your description of how retainers are structured over a 1-year lifespan with monthly-level granularity, the
"missing link" to make those percentages meaningful is Time Elapsed (or "Project Velocity" ).
If we are 50% through the quoted hours, but only 20% through the project's duration (e.g., it's March), we are burning
through the budget way too fast. Conversely, if it's November and we've only burned 50%, we are significantly
under-utilizing the retainer.
The metric we need is Percentage of Time Elapsed (or Elapsed Work Days).
Why this is the "Golden Metric":
By comparing % Hours Burned vs. % Time Elapsed, we get a real-time "Health Score":
* Hours % > Time %: We are "running hot" (over-burning).
* Hours % < Time %: We are "under budget" (under-burning).
* Hours % ≈ Time %: we are perfectly on track.
How to calculate it accurately for your system:
Since you emphasized that "work days" are the source of truth rather than calendar days, the most accurate way to
calculate this would be:
1. Total Work Days in Project: Sum of all work days (minus holidays/weekends) from Project Start Date to Project End
Date.
2. Work Days Elapsed: Sum of all work days from Project Start Date to Today.
3. % Time Elapsed: (Work Days Elapsed / Total Work Days in Project) * 100.
My Proposal for the UI:
Imagine the Project Card having two markers on that progress bar (or a second bar beneath it):
1. The Solid Bar showing % Hours Burned.
2. A Vertical Needle or Ghost Bar showing % Time Elapsed.
If the needle is ahead of the bar, the manager breathes easy. If the bar has passed the needle, it's an immediate
visual red flag.
Is Percentage of Work Days Elapsed the metric you were thinking of?
"missing link" to make those percentages meaningful is Time Elapsed (or "Project Velocity" ).
If we are 50% through the quoted hours, but only 20% through the project's duration (e.g., it's March), we are burning
through the budget way too fast. Conversely, if it's November and we've only burned 50%, we are significantly
under-utilizing the retainer.
The metric we need is Percentage of Time Elapsed (or Elapsed Work Days).
Why this is the "Golden Metric":
By comparing % Hours Burned vs. % Time Elapsed, we get a real-time "Health Score":
* Hours % > Time %: We are "running hot" (over-burning).
* Hours % < Time %: We are "under budget" (under-burning).
* Hours % ≈ Time %: we are perfectly on track.
How to calculate it accurately for your system:
Since you emphasized that "work days" are the source of truth rather than calendar days, the most accurate way to
calculate this would be:
1. Total Work Days in Project: Sum of all work days (minus holidays/weekends) from Project Start Date to Project End
Date.
2. Work Days Elapsed: Sum of all work days from Project Start Date to Today.
3. % Time Elapsed: (Work Days Elapsed / Total Work Days in Project) * 100.
My Proposal for the UI:
Imagine the Project Card having two markers on that progress bar (or a second bar beneath it):
1. The Solid Bar showing % Hours Burned.
2. A Vertical Needle or Ghost Bar showing % Time Elapsed.
If the needle is ahead of the bar, the manager breathes easy. If the bar has passed the needle, it's an immediate
visual red flag.
Is Percentage of Work Days Elapsed the metric you were thinking of?
Now ... I invite someone to explain to me, in all seriousness, that what AI just did here is manifestly different from the general concept of "thinking", as a human would do?
I don't think that is "mindless prediction" based on "word patterns". That's not a "glorified search engine that gives a fancy-sounding answers". That's not "hallucinations", nor did it require the consumption of petabytes of "copyrighted materials" in order to come up with that answer.
By any meaningful definition, AI understands what you're saying, and it's fucking CRAZY how good it is at doing so, and then at problem-solving based on what you prompted it to think about.
AI is going to be humanities downfall, but I'll tell you right now, it won't be because AI "sucks" or is "fake/not real intelligence/not real thinking". It's going to fuck us by the exact opposite means. It's going to outdo us in "intelligence". And by so doing, make BILLIONS of people who make a living by "ability to reason/think" basically obsolete. "Smarts/thinking" will become low-value skills, due to the TERRIFYING and completely UNREGULATED power of AI. Which becomes better at "reasoning" every damn day.
So, after this, I said basically "Exactly! Now, implement that in the code (I like your vertical needle idea), make the little mini-graph on each of the Project cards on the Project Dashboard". 2 minutes later the code was written, and the graphs showing us our project burn-down rates over the year were on the web page in my dev environment
The only way you can keep a job programming computers these days is leveraging AI, because it just did in 2 minutes what it would take me 2 hours to implement myself. At LEAST.
AI is scary because of how *skilled* it is, not how stupid/mindless it is. "We" underestimate it at our own peril.
12 replies
= new reply since forum marked as read
= new reply since forum marked as read