It's amusing to me how people keep trying to apply engineering principles to an inherently unstable and unpredictable system in order to get a feeling of control.
Those prompts should be renamed as hints. Because that's all they are. Every LLM today ignores prompts if they conflict with its sole overarching goal: to give you an answer no matter whether it's true or not.
> Those prompts should be renamed as hints. [...] its sole overarching goal: to give you an answer no matter whether it's true or not.
I like to think of them as beginnings of an arbitrary document which I hope will be autocompleted in a direction I find useful... By an algorithm with the overarching "goal" of Make Document Bigger.
You’re confusing engineering with maths. You engineer your prompting to maximize the chance the LLM does what you need - in your example, the true answer - to get you closer to solving your problem. It doesn’t matter what the LLM does internally as long as the problem is being solved correctly.
(As an engineer it’s part of your job to know if the problem is being solved correctly.)
Maybe very very soft "engineering". Do you have metrics on which prompt is best? What units are you measuring this in? Can you follow a repeatable process to obtain a repeatable result?
> It's amusing to me how people keep trying to apply engineering principles to an inherently unstable and unpredictable system in order to get a feeling of control.
You invoke "engineering principles", but software engineers constantly trade in likelihoods, confidence intervals, and risk envelopes. Using LLMs is no different in that respect. It's not rocket science. It's manageable.
But the threshold between correct and incorrect inference is dependent on an intersection of the model and the document so far. That is not manageable by definition, I mean... It is a chaotic system.
Is this dissimilar to what the human brain produces? Are we not producing chaos controlled by wanting to give the right answer?
Yes it is very dissimilar. Life isn't a sum of the discrete inputs. I mean maybe it is at times but the context is several orders of magnitude greater, the inputs several orders of magnitude input, etc but the theory that it can be quantified like this is unproven let alone a good basis for an artificial system.
> but software engineers constantly trade in likelihoods, confidence intervals, and risk envelopes
Software engineering is mostly about dealing with human limitations (both the writer of the code and its readers). SO you have principles like modularization and cohesion which is for the people working on the code, not the computer. We also have tests, which is an imperfect, but economical approach to ensure the correctness of the software. Every design decision can be justified or argued and the outcome can be predicted and weighted. You're not cajoling a model to get results. You take a decision and just do it.
Engineering principles are probably the best we've got when it comes to trying to work with a poorly understood system? That doesn't mean they'll work necessarily, but...
> Engineering principles are probably the best we've got when it comes to trying to work with a poorly understood system?
At its heart that all engineering principles exist to do. Allow us to extract useful value, and hopefully predictable outcomes from systems that are either poorly understood, or too expensive to economically characterise. Engineering is more-or-less the science of “good enough”.
There’s a reason why computer science, and software engineering are two different disciplines.
From "Modern Software Engineering" by David Farley
> Software engineering is the application of an empirical, scientific approach to finding efficient, economic solutions to practical problems in software.
> The adoption of an engineering approach to software development is important for two main reasons. First, software development is always an exercise in discovery and learning, and second, if our aim is to be “efficient” and “economic,” then our ability to learn must be sustainable.
> This means that we must manage the complexity of the systems that we create in ways that maintain our ability to learn new things and adapt to them.
That is why I don't care about LLMs per se, but their usage is highly correlated to the wish of the user to not learn anything, just have some answer, even incorrect, as long as it passes the evaluation process (compilation, review, ci tests,..). If the usage is to learn, I don't have anything to say.
As for efficient and economical solutions that can be found with them,...
I think you’re being a little over critical of LLMs. They certainly have their issues, and most assuredly people often use them inappropriately. But it rather intellectually lazy to declare that because many people use LLMs inappropriately, that means they can’t offer real value.
I’ve personally found them extremely useful to test and experiment new ideas. Having an LLM throw together a PoC which would have taken me an hour to create, in less than 5mins, is a huge time saver. Makes it possible to iterate through many more ideas and test my understanding of systems far more efficiently than doing the same by hand.
Maybe that’s alien to me because I don’t tend to build PoC, mostly using wireframes to convey ideas. Most of my coding is fully planned to get to the end. The experiment part is on a much smaller scale (module level).
Ah my apologies. I didn’t realise you’re an individual capable of designing and building complex systems made of multiple interconnected novel modules using only wireframes, and having all that work without any prior experimentation.
For the rest of us less fortunate, LLMs can be a fantastic tool to sketch out novel modules quickly, and then test assumptions and interactions between them, before committing to a specific high level design.
> I didn’t realise you’re an individual capable of designing and building complex systems made of multiple interconnected novel modules using only wireframes, and having all that work without any prior experimentation.
Not really. It's just that there's a lot of prior works out there, so I don't need to do experimentation when someone has already done it and describe the lessons learned. Then you do requirement analysis and some designs (system, api, and ux), plus with the platform constraints, there aren't a lot of flexible points left. I'm not doing research on software engineering.
For a lot of projects, the objective is to get something working out there. Then I can focus on refining if needs be. I don't need to optimize every parameter with my own experiments.
How do you handle work that involves building novel systems, where good prior art simply doesn’t exist?
I’m currently dealing with a project that involves developing systems where the existing prior art is either completely proprietary and inaccessible, or public, but extremely nacient and thus documented learnings are less developed than our own learnings and designs.
Many projects may have the primary objective of getting something working. But we don’t all have the luxury of being able to declare something working and walk away. I specifically have requirements around long term evolution of our project (I.e. over a 5-10 year time horizon at a minimum), plus long term operational burden and cost. While also delivering value in the short term.
LLM provide are an invaluable tool for exploring the many possible solutions to what we’re building, and helping to evaluate the longer term consequences of our design decisions, before we’ve committed significant resources to developing them completely.
Of course we could do all this without LLMs, but LLMs substantially increase the distance we can explore before timelines force us to commit.
Maybe the main problem is not solved yet, but I highly doubt that the subproblems are not. Because that would be cutting edge domain, which is very much an outlier.
Ah so what exactly do you mean when you say
> Most of my coding is fully planned to get to the end. The experiment part is on a much smaller scale (module level).
I would seem that these statements taken together mean you don’t experiment at all?
That means that I take time to analyze the problem and come up with a convincing design (mostly research, and experience). After that I've just got a few parameters that I don't know much about. But that doesn't mean that I can't build the stuff. I just isolate them so that I can tweak them later. Why? Because they are often accidental complexities, not essential ones.
> That means that I take time to analyze the problem and come up with a convincing design (mostly research, and experience).
Ah I think we’re finally getting somewhere. My point is that you can use LLM as part of that research process. Not just as a poor substitute for proper research, but as a tool for experimental research. It’s supplemental to the normal research process, and is certainly not a tool for creating final outputs.
Using LLMs like that can make a meaningful difference to speed and quality of the analysis and final design. And something you should consider, rather than dismissing out of hand.
>people keep trying to apply engineering principles to an inherently unstable and unpredictable system in order to get a feeling of control.
What's the alternative?
Using predictable systems.
If your C compiler invents a new function call for a non-existent function while generating code, that's usually a bug.
If an LLM does, that's... Normal. And a non-event.
If we have to use predictable systems, how could we use humans in the first place?
And?
What other engineering domain operates on a fundamentally predictable substrate? Even computer science at any appreciable scale or complexity becomes unpredictable.
Every engineering domain operates within "known bounds". That makes it dependable.
An engineer doesn't just shrug and pick up slag because it contains the same materials as the original bauxite.
Of course not, but how did we get to that point with materials science and chemistry?
We’re basically in the stone ages of understanding how to interact with synthetic intelligence.
Through research and experimentation, yes.
But attempts to integrate little understood things in daily life gave us radium toothpaste and lead poisoning. Let's not repeat stone age mistakes. Research first, integrate later.
Pretending that the world is stable predictable and feeling in control while making fun of other people. Obviously.
Math and physics are pretty stable. So is computer science. Avoid voodoo.
LLMs are just math.
It’s reasonable to scope one’s interest down to easily predictable, simple systems.
But most of the value in math and computer science is at the scale where there is unpredictability arising from complexity.
It's reasonable to perceive most of the value in math and computer science being "at the scale" where there is unpredictability arising from complexity, though scale may not really be the reason for the unpredictability.
But a lot of the trouble in these domains that I have observed comes from unmodeled effects, that must be modeled and reasoned about. GPZ work shows the same thing shown by the researcher here, which is that it requires a lot of tinkering and a lot of context in order to produce semi-usable results. SNR appears quite low for now. In security specifically, there is much value in sanitizing input data and ensuring correct parsing. Do you think LLMs are in a position to do so?
I see LLMs as tools, so, sure I think they’re in a position to do so the same way pen testing tools or spreadsheets are.
In the hands of an expert, I believe they can help. In the hands of someone clueless, they will just confuse everyone, much like any other tool the clueless person uses.
> It's amusing to me how people keep trying to apply engineering principles to an inherently unstable and unpredictable system in order to get a feeling of control.
Are you Insinuating that dealing with unstable and unpredictable systems isn't somewhere engineering principles are frequently applied to solve complex problems?
Are you using 2023 LLMs? o3 and Gemini 2.5 Pro will gladly say no or declare uncertainty in my experience
90% of people only use ChatGTP, typically 4o. Of course you're right, but that's where the disconnect comes from.