LLM Hallucinations in Practical Code Generation (dl.acm.org)

Screenshot of dl.acm.org: LLM Hallucinations in Practical Code Generation

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: AI migrated legacy COBOL programs to Java, bugs included

AI migrated legacy COBOL programs to Java, bugs included (arxiv.org)

65 points by felineflock 2 months ago | 49 comments

Screenshot of simonwillison.net: Hallucinations in code are the least dangerous form of LLM mistakes

Hallucinations in code are the least dangerous form of LLM mistakes (simonwillison.net)

339 points by ulrischa 1 year ago | 264 comments

Simon Willison blog post arguing that LLM hallucinations in code are the least harmful kind of mistake because running the code exposes them immediately.

llm hallucinations ai-assisted-coding code-review

Screenshot of jngiam.bearblog.dev: LLM function calls don't scale; code orchestration is simpler, more effective

LLM function calls don't scale; code orchestration is simpler, more effective (jngiam.bearblog.dev)

251 points by jngiam1 1 year ago | 90 comments

Screenshot of arxiv.org: How Well Do LLMs Generate Code for Different Application Domains?

How Well Do LLMs Generate Code for Different Application Domains?(arxiv.org)

56 points by belter 1 year ago | 19 comments

Screenshot of arxiv.org: Paper2Code: Automating Code Generation from Scientific Papers

Paper2Code: Automating Code Generation from Scientific Papers (arxiv.org)

122 points by Jerry2 1 year ago | 23 comments

Screenshot of dl.acm.org: Magnetic Tape Storage Technology: usage, history, and future outlook

Magnetic Tape Storage Technology: usage, history, and future outlook (dl.acm.org)

35 points by matt_d 1 year ago | 12 comments

Looks similar

AI migrated legacy COBOL programs to Java, bugs included(arxiv.org)

Hallucinations in code are the least dangerous form of LLM mistakes(simonwillison.net)

LLM function calls don't scale; code orchestration is simpler, more effective(jngiam.bearblog.dev)