Claim · 2021-09-21 · publication · Stated in source · Supported

Why AI alignment could be hard with modern deep learning cites Language Models are Few-Shot Learners.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Why AI alignment could be hard with modern deep learning → cites → Language Models are Few-Shot Learners

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Why AI alignment could be hard with modern deep learningcites ↓Language Models are Few-Shot Learners

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2021-09-21 · publication Records dated 2021 →

Scope and limitsAn explicit reference only; neither agreement nor influence. The citing text does not identify which version of the work was read.

The evidence 01

primary sourceSupports the claim

Why AI alignment could be hard with modern deep learning

Cold Takes (Holden Karnofsky’s blog), guest post · 2021-09-21

Archived copy, captured 2021-09-21: Why AI alignment could be hard with modern deep learning

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Paraphrase

The text gives the arXiv identifier 2005.14165.

Location in source reference by arXiv identifier

Machine-checked · 2026-10-31

Source details and check notes

Authors: Ajeya Cotra
Version: Current page, retrieved 2026-10-06 with the hash recorded by the 1996–2022 candidate search; the quote also matches the raw capture of 2021-09-21, re-verified for this collection.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-06
Language: English (en)
Archive copy: Open archived copy, captured 2021-09-21: Why AI alignment could be hard with modern deep learning. Captured on the recorded publication date. An archive copy shows only what the archive retrieved on 2021-09-21. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.
Attribution: Ajeya Cotra, "Why AI alignment could be hard with modern deep learning", Cold Takes, 21 September 2021.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, key papers (research/key-papers). The citation was matched (arXiv identifier) in the text retrieved for the candidate pack on 2026-10-28 and re-found by its mechanical check. The paraphrase is Selekoa’s. A cross-family machine check (2026-10-30, item B062) found the citation in the citing text. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. An explicit reference to a work. Citation alone is neither agreement nor causal influence.

Date. Date of the citing source as recorded in the dataset; unknown where the dataset has none.

Record ID kp-cites-cotra-2021-why-ai-alignment-could-be-hard-language-models-few-shot-learners-2020