Verified claim · AI-ML · 100% confidence
InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 590b9de765b8126e
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Structured fields
- Subject
- InstructGPT
- Predicate
introduced_in- Object
- Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT
- Confidence
- 100%
- Tags
- instructgpt · openai · rlhf · alignment · foundational · 2022 · introduced_in
Sources (2)
[1] preprint · arXiv (Ouyang, Wu, Jiang, Almeida, Wainwright, Mishkin, Zhang, Agarwal, et al. / OpenAI) · 2022-03-04
Training language models to follow instructions with human feedback“Making language models bigger does not inherently make them better at following a user's intent. In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback.”
[2] official blog · OpenAI · 2022-01-27
Aligning language models to follow instructionsOpenAI is rated by SourceScore — see its reliability →
Cite this claim
Ready-to-paste citation (Markdown / plain text):
InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT. — SourceScore Claim 590b9de765b8126e (verified 2026-05-16). https://sourcescore.org/api/v1/claims/590b9de765b8126e.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/590b9de765b8126e/" width="100%" height="360" frameborder="0" loading="lazy" title="InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
InstructGPT methodology introduced in paper: Training language models to follow instructions with human feedback (Ouyang et al., 2022).
5da8f8dffc038b8e · 100% confidence · shares 5 tags (instructgpt, alignment, openai…)
Anthropic Constitutional AI Harmlessness introduced in paper: Bai et al. 2022 — training a helpful and harmless assistant.
6fa575eb9df5ac32 · 100% confidence · shares 4 tags (alignment, foundational, 2022…)
Reinforcement Learning from Human Feedback (RLHF) introduced in paper: Deep Reinforcement Learning from Human Preferences (Christiano et al., 2017).
67866330cd60e54d · 100% confidence · shares 3 tags (rlhf, alignment, foundational)
Proximal Policy Optimization (PPO) introduced in paper: Proximal Policy Optimization Algorithms (Schulman et al., 2017).
00f224e1ccc158ef · 100% confidence · shares 3 tags (foundational, openai, rlhf)
Speculative decoding introduced in: Leviathan, Kalman, Matias 2023 — Google Research.
6cdc7730bf41bb3d · 100% confidence · shares 3 tags (foundational, 2022, introduced_in)
Frequently asked questions
Is the claim "InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT." verified?
Yes — SourceScore verified this claim with 100% confidence as of 2026-05-16. The verification uses 2 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT."?
Evidence comes from 2 primary sources: arXiv (Ouyang, Wu, Jiang, Almeida, Wainwright, Mishkin, Zhang, Agarwal, et al. / OpenAI), OpenAI. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/590b9de765b8126e.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-16 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/590b9de765b8126e.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/590b9de765b8126e.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/590b9de765b8126e.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/590b9de765b8126e.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "InstructGPT introduced in: Ouyang et al. 2022 — RLHF-tuned GPT-3, direct ancestor of ChatGPT."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_instructgpt_fact() -> dict:
"""Fetch the verified SourceScore claim for InstructGPT."""
r = httpx.get("https://sourcescore.org/api/v1/claims/590b9de765b8126e.json")
return r.json()