Newer AI Coding Assistants Are Failing in Insidious Ways

Comments

• unexposedhazard@discuss.tchncs.de ⁨1⁩ ⁨day⁩ ago

  I use LLM-generated code extensively in my role as CEO of Carrington Labs, a provider of predictive-analytics risk models for lenders.

  Well you know where not to buy now…

  source

  • panda_abyss@lemmy.ca ⁨23⁩ ⁨hours⁩ ago

    Oh yeah, I read that and thought “this has all the problems of the garden of forking paths”

    Based on the description, the whole company is just p-hacking. There’s a reason why nobody uses stepwise feature selection, you just replaced the evaluation/step mechanism with AI.

    source
• Feyd@programming.dev ⁨1⁩ ⁨day⁩ ago

  Unexpected???

  source

  • TaviRider@reddthat.com ⁨1⁩ ⁨day⁩ ago

    Unexpected to AI true believers.

    source

    • WanderingThoughts@europe.pub ⁨1⁩ ⁨day⁩ ago

      I’ve lived long enough to go through multiple AI winters. This is just business failure as usual.

      source
  • luciferofastora@feddit.org ⁨1⁩ ⁨day⁩ ago

    Unexpected in the same way as you don’t expect leopards to eat your face…

    source
• nightlily@leminal.space ⁨1⁩ ⁨day⁩ ago

  Paint huffer surprised when other paint huffers are happy to accept any old solvent.

  source
• riskable@programming.dev ⁨1⁩ ⁨day⁩ ago

  Correction: Newer versions of ChatGPT (GPT-5.x) are failing in insidious ways. The article has no mention of the other popular services or the dozens of open source coding assist AI models (e.g. Qwen, gpt-oss, etc).

  The open source stuff is amazing and gets better just as quickly as the big AI options. Yet they’re boring so they don’t make the news.

  source

  • count_dongulus@lemmy.world ⁨1⁩ ⁨day⁩ ago

    That’s because OpenAI is in panic mode. They’re now spending their resources on making the LLM cheaper to operate and capable of injecting paid results.

    source
• atrielienz@lemmy.world ⁨1⁩ ⁨day⁩ ago

  GiGo.

  source
• 1Fuji2Taka3Nasubi@piefed.zip ⁨1⁩ ⁨day⁩ ago

  Not failing, just Skynet doing its work.

  source