Thread

1. askonomm · 1790605097 · focus · HN ↗

   What I've found is that AI allows lazy and incompetent developers to be more lazy and more incompetent. This then has the effect that product quality suffers more, faster. As a result of the sheer amount of code now being pushed out, code reviews, a thing that previously somewhat prevented lazy and incompetent developers from pushing out horrible code, is effectively dead in the water since no human can actually review such amounts of code realistically anymore. Some companies have adopted AI to review code, which, well ... you have AI make code, AI review code ... I hope you can see the stupidity here if you expect to see any deterministic results at all.

   I guess time will tell if the consumer will adapt to the lower quality of products, allowing companies to justify the existence of lazy and incompetent developers, or if the consumer will push back, forcing companies to increase the quality of their developers.

   Note: I use AI every day and it is entirely possible to create high quality software with it, so long as you are not lazy and incompetent.

   1. whatever1 · 1790605354 · focus · HN ↗

      Even if you are competent I cannot review your 5,000 lines of code you produce per day vs the 100 you were producing before the LLM apocalypse.

      1. rfgplk · 1790605820 · focus · HN ↗

         5,000 is the output velocity of someone not fully immersed in agentic coding. I've seen repos do ~100k to ~250k loc changes per week.

         1. 0c3ca83 · 1790606842 · focus · HN ↗

            Yes, they're certainly squeezing 500 lines of functionality into 250,000 lines of code. Agents are great at this.

            1. bitwize · 1790609916 · focus · HN ↗

               Tell me you're not using a frontier model without telling me you're not using a frontier model

               1. paganel · 1790610455 · focus · HN ↗

                  Where's the great software, then? I'm genuinely asking: where is it? Because I can't find it, and it's been close to a year since AI for programming has started to take off.

                  1. dawnerd · 1790610908 · focus · HN ↗

                     In fact, a lot of the once great software that's switched to AI driven development has gotten worse.

                     1. cat-snatcher · 1790611649 · focus · HN ↗

                        For example?

                        1. 0c3ca83 · 1790614035 · focus · HN ↗

                           Google.

                           1. cat-snatcher · 1790614947 · focus · HN ↗

                              It was going downhill way before AI.

                              1. intrikate · 1790617123 · focus · HN ↗

                                 That's true, but also doesn't prevent the accelerated decay that it seems to be undergoing since AI hit the scene en masse a few years ago.
                        2. dawnerd · 1790617048 · focus · HN ↗

                           Clickup. Windows. Github, VSCode...

                           Could be argued they were going downhill before but it's a much faster decline since 2023-ish

                           1. necovek · 1790622201 · focus · HN ↗

                              Somebody posted that GitHub status summary: in ten years, they averaged 10 incidents per month — this includes the last 12 months. In the last six months, average is 22.
               2. 0c3ca83 · 1790610876 · focus · HN ↗

                  Tell me you never once bothered to look at the generated code without telling me you don't look at the generated code.

                  Luajit is under 80,000 lines of code.

               3. whateveracct · 1790618770 · focus · HN ↗

                  i have unlimited tokens and i throw Fable / Astra at everything. They suck ass still for anything nontrivial. I could commit that garbage but if I kept doing it, I will end up with a ball of mud only Fable / Astra can grok..convenient for Dario and SamA..
               4. necovek · 1790622036 · focus · HN ↗

                  I've asked Codex with GPT 6 Astra to *review" a one time benchmarking script for any mistakes (built by Claude Code using Opus 5.5) and it refactored the shit out of it claiming all sorts of stuff without even asking about the context in which it was developed.

                  If I was to employ them to review the code without giving each the same baseline multi-page prompt, they go into endless loop of "improvement" with no end goal in sight.

                  More and more frequently, I instruct frontier models to stop and go back to the task at hand.

                  1. vandopereira · 1790733134 · focus · HN ↗

                     [dead]

               5. perrygeo · 1790712428 · focus · HN ↗

                  Frontier models are subjectively worse at this, in my experience. Very intelligent but very prone to expanding scope. I need to spend more time prompting to get good results. Maybe I'm just working on boring stuff that doesn't require "frontier" intelligence?

Unofficial Hacker News client; not affiliated with Y Combinator.