Phrases.pdf – How Well Do LLM Predictions Compare with Actual Corpus Data
Postedabout 2 months agoActiveabout 2 months ago
english-corpora.orgTechstory
calmneutral
Debate
0/100
LLM PredictionsCorpus DataAI WritingNatural Language Processing
Key topics
LLM Predictions
Corpus Data
AI Writing
Natural Language Processing
Analysis of LLM predictions compared to actual corpus data, with discussion on identifying AI-generated writing.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
4m
Peak period
1
0-1h
Avg / period
1
Key moments
- 01Story posted
Nov 19, 2025 at 8:56 PM EST
about 2 months ago
Step 01 - 02First comment
Nov 19, 2025 at 9:00 PM EST
4m after posting
Step 02 - 03Peak activity
1 comments in 0-1h
Hottest window of the conversation
Step 03 - 04Latest activity
Nov 19, 2025 at 9:00 PM EST
about 2 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
Discussion (1 comments)
Showing 1 comments
mefenglAuthor
about 2 months ago
this explains why llm writing is easy to spot if you read a lot, the phrases they use are different from real text
View full discussion on Hacker News
ID: 45987890Type: storyLast synced: 11/22/2025, 8:34:09 AM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.