Looks similar
How AI text watermarking works(declaude.org)
86 points by padolsey | 59 comments
Embeddings are underrated(technicalwriting.dev)
271 points by misonic | 138 comments
Detecting when LLMs are uncertain(thariq.io)
257 points by trq_ | 148 comments
Related stories
Embeddings are underrated (2024)(technicalwriting.dev)
441 points by jxmorris12 | 133 comments
An essay arguing that text embeddings are an underrated machine learning tool, especially for technical writing and documentation work.
Bad numbers in the “gzip beats BERT” paper?(kenschutte.com)
341 points by ks2048 | 109 comments
Blog post arguing the "gzip beats BERT" text classification paper reports top-2 accuracy instead of kNN(k=2) accuracy due to a code bug, inflating results.
How I, a beginner developer, read the tutorial you, a developer, wrote for me(anniemueller.com)
782 points by wonger_ | 363 comments
A humorous blog post parodying how developer-written tutorials full of jargon read to a non-developer beginner.
Ask HN: How can I get better at using AI for programming?
375 points by lemonlime227 | 379 comments
Ask HN post asking for tips on using AI tools like Claude Code to better migrate a jQuery and Django project to idiomatic SvelteKit.
Ask HN: How are you acquiring your first hundred users?
463 points by amanchanda | 285 comments
Ask HN thread where a founder of a $50/month B2C AI SaaS asks how others acquired their first 100 and next 500 users.
“A calculator app? Anyone could make that”(chadnauseam.com)
1683 points by pie_flavor | 407 comments
Blog post retelling a tweet thread on why building an accurate calculator app is hard, covering precision issues like (10^100)+1-(10^100) returning 0.











