1. I mean, yes ? the average farm worker is probably capable of writing a sentence similar to the one you just did and sicking it a prompt.
Unless you mean without LLM assistance, then no.
2. I've no idea, i haven't touched c++ in an age, if i got back up to speed then possibly.
3. To learn how to program in c++ again, figure out best practices and then write the code? A while probably.
But then i'd have to to that anyway to be able to spot any problems in the code and know what to test.
because i'm for sure not putting code out there that i don't understand, especially when the code has been generated by a non-deterministic system prone to subtle hallucinations.
I'm not saying LLM's have no uses, they do some things fine, inflating the capabilities of a tool because of hype isn't a viable mid to long term strategy.
LLM's are poor(but improving in some ways) at consistent multiple-boundary complexity.
My issue wasn't with the statement itself, just that is was very broad, hence my reply.
LLMs can assist with all of those steps, potentially, if you use them for the things they are suited for and have a plan for maintaining quality and consistency beyond "let the LLM's review and test it for me", i'd consider that professional negligence given the current SOTA.
The assistance should be subject an accurate cost/benefit analysis before implying the assistance is worthwhile, was my point.
If it's working for you, great, but presenting it like it's a general direct replacement for development teams is disingenuous.
---
> Looks like we just have different expectations: i don't want to micromanage my coding agents any more than i micromanage the developers i work with as a product manager. If the output does what it is supposed to do, and the software is maintainable and extendable by following certain best practices, i'm happy. And i expect that goes for most business people.
None of what i said implied any expectations of the process of using the tools, but if you've found something that works for you that's good.
On the subject of maintainability and extension, that is usually bound to the level of complexity of the project and the increase in requirements is not generally linear.
I agree, many business people would love what you've described, very few are getting it.
> And in practice i have more control with a coding agent than with developers as i can iterate over ideas quickly: "build this idea", "no change this", "remove this and replace it with this". Within an hour you can quickly iterate an idea into something that works well. With developers this would have taken days if not more. And they would've complained i need to better prepare my requirements.
Up to a point, yes.
If your application of this methodology works well enough before you hit the limitations of the tooling, that's great.
There is , however, a threshold of complexity where this starts to break down, this threshold can be mitigated somewhat with experience and a better understanding on how to utilise the tooling, but it still exists (currently).
Once you reach this threshold the approaches you are talking about start to work less effectively and even actively hinder progress.
There are techniques and approaches to software development that can further push this threshold out, but then you're getting into the territory of having to know enough to be able to instruct the LLM to use these approaches.
This is probably just a disagreement about the term "control", so we can agree to disagree on that one i suppose.
The rest of the reply doesn't really relate to any of the points i mentioned.
That it's possible to successfully use the tool to achieve your goals wasn't in dispute.
I'll try to narrow it down:
---
> You are not a victim at the mercy of your LLM.
Yes, you absolutely are, it's how they work.
As i said, you can suggest guidelines and directions but it's not guaranteed they'll be adhered to.
To be clear , this also applies to people as well.
---
Directing an LLM (or LLM based orchestration system) is not the same as directing a team of people.
The "interface" is similar in that you provide instructions and guidelines and receive an attempt at the wanted outcome.
However, the underlying mechanisms of how they work are so different that the analogy you were trying to use doesn't make sense.
---
Again, LLM's can be useful tools, but presenting them as something they aren't only serves to muddy the waters of understanding how best to use them.
---
As an aside, IMO, the sketchy salesmen approach to over-promising on features and obscuring the the limitations will do great harm to the adoption of LLM's in the medium to long term.
The misrepresentation of terminology is also contributing to this.
The term AI is intentionally being used to attribute a level of reasoning and problem solving capability beyond what actually exists in these systems.
> You have a lot of control over what the LLM creates.
No, you don't, you have "influence" or "suggestion".
You can absolutely narrow down the probability ranges of what is produced , but there is no guarantee that it will stick to your guidelines.
So far, at least, it's just not how they work.
> You don't have 100% control over what your LLM devs are doing, but more than you think. Just like normal managers don't micromanage every action of their team.
This overlooks the role of actual reasoning/interpretation that is found when dealing with actual people.
While it might seem like directing an LLM is similar in practice to managing a team of people, the underlying mechanisms are not the same.
If you analyse based on comparisons between those two approaches, without understanding the fundamental differences in what's happening beneath the surface, then any conclusions drawn will be flawed.
---
I'm not against LLM's, i'm against using them poorly and presenting them as something they are not.
Isn't the whole point of amphetamine based treatement for ADHD to correct(or beneficially alter, depending on your point of view) an non-standard brain chemistry?
AFAIK some neurodivergent brains deal with amphetamines differently and the baseline levels of chemical affected by amphetamines is different.
Wear and tear might be a thing, i don't know, but the analogy of putting NO2 in their car feels a bit off.
It'd be more like finally putting premium unleaded in your car after years of "back of the lorry" pseudo-unleaded.
Unless you mean without LLM assistance, then no.
2. I've no idea, i haven't touched c++ in an age, if i got back up to speed then possibly.
3. To learn how to program in c++ again, figure out best practices and then write the code? A while probably.
But then i'd have to to that anyway to be able to spot any problems in the code and know what to test.
because i'm for sure not putting code out there that i don't understand, especially when the code has been generated by a non-deterministic system prone to subtle hallucinations.
I'm not saying LLM's have no uses, they do some things fine, inflating the capabilities of a tool because of hype isn't a viable mid to long term strategy.
LLM's are poor(but improving in some ways) at consistent multiple-boundary complexity.
My issue wasn't with the statement itself, just that is was very broad, hence my reply.
LLMs can assist with all of those steps, potentially, if you use them for the things they are suited for and have a plan for maintaining quality and consistency beyond "let the LLM's review and test it for me", i'd consider that professional negligence given the current SOTA.
The assistance should be subject an accurate cost/benefit analysis before implying the assistance is worthwhile, was my point.