Zum Inhalt springen
KI-Atlas

Codegenerierung

Aus einer Beschreibung lauffähigen Code schreiben

Code & SoftwareAnfänger #33
EingabeTextCode

Der vollständige Artikel liegt auf Englisch vor; Titel und Zusammenfassung sind lokalisiert.

WAS DIESE FÄHIGKEIT BEDEUTET

Takes a description — write a function that reads a CSV into a list of dicts and skips blank lines — and outputs the corresponding source. Unlike code completion it targets a new feature or a whole piece of logic, usually written from scratch; unlike reasoning the deliverable is compilable, runnable code rather than a textual conclusion.

Wie sie technisch umgesetzt wird

The base is a language model pre-trained on large code corpora; strict syntax makes code easier to verify by execution than prose, so unit-test pass signals work well as reward for reinforcement learning or rejection-sampling fine-tuning. Training and evaluation use problems with test cases such as HumanEval and MBPP, and generation can sample several candidates and discard the ones that fail.

Repräsentative Produkte

11

Beteiligte Organisationen

Typische Verwendungen

  • New features and utility scripts
  • Data cleaning and transformation scripts
  • Test cases and project scaffolding
  • Porting code across languages and frameworks

Wie sie bewertet wird

pass@k
Share of problems with at least one sample passing all tests out of k
Benchmark pass rate
Pass rate on fixed sets such as HumanEval
Compile and lint pass rate
Whether generated code passes the compiler and type checks as-is

Grenzen und schwierige Punkte

  • It invents libraries or methods, producing plausible interfaces that do not exist
  • Code can pass unit tests yet leave holes in edge cases, error handling and security
  • Multi-file changes are inconsistent, with call sites disagreeing with definitions

Konzepte dahinter