11–20 of 40 posts
Lived experience says different.
This is literally what the study says: the developers said they felt they were faster after having completed the task, when in fact they were slower. Your "lived experience" just follows the same bias.
Actual tangible real results say different.
I know the anti AI folks would like to believe AI coding results are a mass hallucination but the completed software that I build in record time with deep functionality says otherwise.
The perception that AI tools make development faster is perhaps due to the part we spend a lot of time with thinking about how to write (like commenting) is solved instantly.
I think a lot of the delay is that it’s a new class of tool, and just like last gen IDE it takes a bit of getting used to and know where their strengths are, and know how to effectively fit it into your workflow.
I want to believe that this is true. But I don't.
Earlier quoted context omitted.
This is literally what the study says: the developers said they felt they were faster after having completed the task, when in fact they were slower. Your "lived experience" just follows the same bias.
Ok let me rephrase. Actual tangible real results say different. I know the anti AI folks would like to believe AI coding results are a mass hallucination but the completed software that I build in record time with deep functionality says otherwise.
Got some data?
Earlier quoted context omitted.
This is literally what the study says: the developers said they felt they were faster after having completed the task, when in fact they were slower. Your "lived experience" just follows the same bias.
Ok let me rephrase. Actual tangible real results say different. I know the anti AI folks would like to believe AI coding results are a mass hallucination but the completed software that I build in record time with deep functionality says otherwise.
Unless you've timed yourself doing the same task once with AI and once without, while having forgotten everything about said task in meantime, you don't have tangible real results that show otherwise.
Earlier quoted context omitted.
Ok let me rephrase. Actual tangible real results say different. I know the anti AI folks would like to believe AI coding results are a mass hallucination but the completed software that I build in record time with deep functionality says otherwise.
I feel LLMs save me time too but I worry my perceptions don't match the reality. Got some data?
There is nothing I could say that would convince a skeptic.
Earlier quoted context omitted.
I feel LLMs save me time too but I worry my perceptions don't match the reality. Got some data?
>> Got some data? There is nothing I could say that would convince a skeptic.
You’d need probably at least 30 to 40 people (there’s ways to estimate this, but this is gut feeling from years ago when I did studies like this)
It would take on a few flaws in tfa which has a low number of people who operate in a codebase that they know very well on issues that they self-selected (and thus already will have a (perhaps subconscious) strategy for).
That would help convincing skeptics.
In my experience, I don’t think hallucinations are a big problem anymore in terms of coding as long as you work within your domain of expertise. The perception that AI tools make development faster is perhaps due to the part we spend a lot of time with thinking about how to write (like commenting) is solved instantly. I think a lot of the delay is that it’s a new class of tool, and just like last gen IDE it takes a b…
Well, unless of course you are building low-risk software in which you don't care about it's correctness then sure.
> ...as long as you work within your domain of expertise.
But again, try tell that to the "vibe-coders" who get stuck when AI agents continue to insert bugs they cannot find.