Skip to main content
Discovery icon for BendersMC Discord server

BendersMC

14,116 Online
140,043 Members
💬︱general5 people

LLM limits for novel coding

LLMs struggle to write code for original languages or projects outside their training data, despite performing well on familiar codebases.

  • LLMs fail to produce functional code when dealing with completely novel projects or languages absent from their training sets
  • Models succeed on niche tasks like programming calculator games when existing source examples are supplied or present in training data
  • Transformer-based models act as prediction engines, making them reliable primarily for familiar programming domains
Summarized from recent messages, might be inaccurate

More conversations

💬︱general

balancing pvp mechanics

💬︱general

how to toggle bending

💬︱general

server monetization and Project Appa

💬︱general

anime and manga recommendations

Talk, Play, &
Hang Out

Find your space to hang out, discuss the latest updates with the party chat, and see who's down to join your next match.
Get App