Side N
Everyone Agrees You Should Write Loops. Nobody Agrees What One Is.
Which sources back which section of this article, and what its evidence base looks like.
Which sources back which section
| Section | Sources behind it |
|---|---|
| What It Is | Michael Bolin, OpenAI; WorkOS, event page; Boris Cherny on X; WorkOS, video page; Noelle Festa, WorkOS; Microsoft Build, session BRK245; Peter Steinberger on X, 7 Jun; Addy Osmani; Ezekiel Njuguna, Medium; Peter Steinberger on X, 11 Jun; Brent D. Griffiths, Business Insider; Armin Ronacher; Andrew Ng on X; Delba de Oliveira and Michael Segner, Claude blog; Wang et al., LoopArena, arXiv |
| Timeline | Yao et al., ReAct, arXiv; Geoffrey Huntley; Michael Bolin, OpenAI; WorkOS, event page; Boris Cherny on X; Liu et al., arXiv; WorkOS, video page; Noelle Festa, WorkOS; Microsoft Build, session BRK245; Peter Steinberger on X, 7 Jun; Addy Osmani; Ezekiel Njuguna, Medium; Peter Steinberger on X, 11 Jun; Brent D. Griffiths, Business Insider; Armin Ronacher; Andrew Ng on X; Delba de Oliveira and Michael Segner, Claude blog; John K. Waters, ADTmag; Wang et al., LoopArena, arXiv |
| The Argument | Yao et al., ReAct, arXiv; Geoffrey Huntley; Michael Bolin, OpenAI; Addy Osmani; Ezekiel Njuguna, Medium; Brent D. Griffiths, Business Insider; Armin Ronacher; Andrew Ng on X; Delba de Oliveira and Michael Segner, Claude blog |
| What Others Add | Microsoft Build, session BRK245; Addy Osmani; Peter Steinberger on X, 11 Jun; Brent D. Griffiths, Business Insider; Armin Ronacher; Delba de Oliveira and Michael Segner, Claude blog; Wang et al., LoopArena, arXiv |
| Conclusion | Yao et al., ReAct, arXiv; Geoffrey Huntley; Michael Bolin, OpenAI; Microsoft Build, session BRK245; Peter Steinberger on X, 7 Jun; Addy Osmani; Armin Ronacher; Delba de Oliveira and Michael Segner, Claude blog; Wang et al., LoopArena, arXiv |
What the evidence base looks like
- 19Sources behind this article
- 5Sections, every one of them sourced
- 16Read in full
- 3Read at the abstract or opening only
| What the source is | How many | How they were read |
|---|---|---|
| Origin: the paper, post, talk or event record in which a technique, a term, a remark or a measurement first appeared | 11 | Ten in full; one video page for its title, date and description only — the recording was not watched |
| Vendor: a company writing about its own product or event | 3 | All three in full; what they say about themselves is on the page as theirs |
| Reporting: journalism about the term | 2 | Both in full; one quotation they report could not be traced and is attributed to them |
| Community: practitioners writing on their own account | 2 | One in full; one at its opening only, the rest being for members |
| Reference: an analysis of a product's public source code | 1 | At the abstract; used for one sentence it states directly |
Reliable
Reliable, but with an interestWorth believing and reliableWeak on both, and used with careHonest, but thin
Worth believing