The AI coding trap

Post by djeastm » Sun, Sep 28, 2025, 10:38 PM UTC

BowBun wrote: post #94

For now, my mind is still made up. I leave the door open to be shown any serious piece of software that is built primarily through agentic workflows. Having tried to use these tools over the past month to build a critical piece of infrastructure for my company, I agree with OP. I spent so much time wrangling back unnecessary garbage that the LLM found was important, that I wondered if just writing it in one shot woul…

Post by wilsonnb3 » Sun, Sep 28, 2025, 10:46 PM UTC

mordymoop wrote: post #91

Broadly the critique is valid where it applies; I don’t know if it accurately captures the way most people are using LLMs to code, so I don’t know that it applies in most case. My one concrete pushback to the article is that it states the inevitable end result of vibe coding is a messy unmaintainable codebase. This is empirically not true. At this point I have many vibecoded projects that are quite complex but work p…

Post by badsectoracula » Sun, Sep 28, 2025, 11:09 PM UTC

didibus wrote: post #93

badsectoracula wrote: post #14

Earlier quoted context omitted.

> the LLM may not be learning anything, but I am Regardless of that, personally i'd really like it if they could actually learn from interacting with them. From a user's perspective what i'd like to do is to be able to "save" the discussion/session/chat/whatever, with everything the LLM learned so far, to a file. Then later be able to restore it and have the LLM "relearn" whatever is in it. Now, you can already do th…

You want something that requires an engineering breakthrough. Models don't have memory, and they don't have understanding or intelligence beyond what they learned in training. You give them some text (as context), and they predict what should come after (as the answer). They’re trained to predict over some context size, and what makes them good is that they learn to model relationships across that context in many dim…

Post by mehagar » Sun, Sep 28, 2025, 11:14 PM UTC

qazxcvbnmlp wrote: post #151

What these articles miss: 1) not all coding is the same. You might be working on a production system. I might need a proof of concept 2) not everyone's use of the coding agents is the same 3) developer time, especially good developer time has a cost too I would like to see an article that frames the tradeoffs of AI assisted coding. Specifically without assigning value judgments (ie goodness or badness). Really hard w…

Post by AdieuToLogic » Sun, Sep 28, 2025, 11:23 PM UTC

baq wrote: post #117

PessimalDecimal wrote: post #87

Earlier quoted context omitted.

> What's the difference between a messy codebase created by a genAI, and a messy codebase where all the original authors of the code have moved on and aren't available to ask questions? The difference is the hope of getting out of that situation. If you've inherited a messy and incoherent code base, you recognize that as a problem and work on fixing it. You can build an understanding of the code through first reading…

> You're constantly back at Day 1 of having to "own" someone else's code. If only there were some people in software engineering in this situation before AI… oh wait. In the current times you’re either an agent manager or you’re in for a surprise.

  In order to use LLM's to generate code, the engineer
  has to understand the problem sufficient enough to
  formulate prompt(s) to use in order to get usable
  output (code).  Assuming the engineer has this level
  of understanding along with knowledge of the target
  programming language and libraries used, how is using
  LLM code generation anything more than a typing saver?