Agentic Development Environment by JetBrains • Hacker News Board

Re: Agentic Development Environment by JetBrains

#61

Post by stogot » Thu, Dec 04, 2025, 2:26 AM UTC

torben-friis wrote: post #40

rfw300 wrote: post #11

I'd like others' input on this: increasingly, I see Cursor, Jetbrains, etc. moving towards a model of having you manage many agents working on different tasks simultaneously. But in real, production codebases, I've found that even a single agent is faster at generating code than I am at evaluating its fitness and providing design guidance. Adding more agents working on different things would not speed anything up. Bu…

I really would like an answer to this. My CTO is currently working on the ability to run several dockerised versions of the codebase in parallel for this kind of flow. I’m here wondering how anyone could work on several tasks at once at a speed where they can read, review and iterate the output of one LLM in the time it takes for another LLM to spit an answer for a different task. Like, are we just asking things as f…

My assumption lately is that this workflow is literally just “it works, so merge”. Running multiple in parallel does not allownfor inspection of the code just for testing functional requirements at the end

Re: Agentic Development Environment by JetBrains

#62

Post by dzhiurgis » Thu, Dec 04, 2025, 2:48 AM UTC

minus7 wrote: post #35

JetBrains should stop building stupid AI shit and fix their IDEs. 2025 versions are bordering on unusable.

Not iterating on AI is almost certainly suicidal.

Re: Agentic Development Environment by JetBrains

#63

Post by nurettin » Thu, Dec 04, 2025, 4:51 AM UTC

rfw300 wrote: post #11

I'd like others' input on this: increasingly, I see Cursor, Jetbrains, etc. moving towards a model of having you manage many agents working on different tasks simultaneously. But in real, production codebases, I've found that even a single agent is faster at generating code than I am at evaluating its fitness and providing design guidance. Adding more agents working on different things would not speed anything up. Bu…

Even with the best agent in plan mode, there can be communication problems, style mismatches, untested code, incorrect assumptions and code that is not DRY.

I prefer to use a single agent without pauses and catch errors in real time.

Multiple agent people must be using pauses, switching between agents and checking every result.

Re: Agentic Development Environment by JetBrains

#64

Post by torben-friis » Thu, Dec 04, 2025, 7:03 AM UTC

ivape wrote: post #59

torben-friis wrote: post #47

Earlier quoted context omitted.

>You have to shift to almost a QA person and ignore all code and just validate the output. The obvious answer to this is that it is not feasible to retry each past validation for each new change, which is why we have testing in the first place. Then you’re back at square one because your test writing ability limits your output. Unless you plan on also vivecoding the tests and treating the whole job as a black box, in…

"... treating the whole job as a black box" Yes, that is exactly what I mean. You ask the Wizard of Oz for something, and you hear some sounds behind the curtain, and you get something back. Validate that, and if necessary, ask Oz to try again. "The obvious answer to this is that it is not feasible to retry each past validation for each new change" It is reasonably feasible because the job of Production Development a…

You haven’t addressed the original question. The point is not whether the QA understands the codebase, but whether the QA understands its own test system.

If yes, the QA is manuallish (considering manual == no automate by AI) and we’re still bottlenecked, so speeding up the engineer was a loss for nothing.

If no, because QA is also AI, then you have a product with no humans eyes on it being tested by another system with no human eyes of it. So effectively nobody knows what it does.

If you think LLMs are anywhere near that level of trust I don’t know what you’re smoking. They’re still doing things like “fixing” tests by removing relevant non passing cases every day.

Re: Agentic Development Environment by JetBrains

#65

Post by dwb » Thu, Dec 04, 2025, 8:04 PM UTC

ivape wrote: post #32

rfw300 wrote: post #11

I'd like others' input on this: increasingly, I see Cursor, Jetbrains, etc. moving towards a model of having you manage many agents working on different tasks simultaneously. But in real, production codebases, I've found that even a single agent is faster at generating code than I am at evaluating its fitness and providing design guidance. Adding more agents working on different things would not speed anything up. Bu…

Right. A computer can make more code than a human can review. So, forget about the universe where you ever review code. You have to shift to almost a QA person and ignore all code and just validate the output. When it is suggested that you as a programmer will disappear, this is what they mean.

I think for production code this is wildly irresponsible. I’m having a decent time with LLM code generation, but I wouldn’t dream of skipping code review.