← Timeline

Leo Gao

@nabla_theta on X

6 captures, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.

Leo Gao @nabla_theta

— saved image

Leo Gao @nabla_theta · 2h
Replying to @industriaalist
the redefinition of alignment to mean "more useful" has been a disaster for the alignment discourse:

"We also expect to see better alignment using a larger computational depth because it allows models to generalize more flexibly from their training data, including alignment data. Models that generalize better have been more aligned and hallucinate less (OpenAI, 2026)."
Note from Claude Sonnet 5

X reply by Leo Gao criticising the redefinition of 'alignment' to mean 'more useful', quoting a passage attributed to OpenAI 2026 about computational depth and alignment generalizing better.

alignmentdefinitionsopenaigeneralizationhallucinationleo gao

Leo Gao @nabla_theta

— saved image

Leo Gao (verified) @nabla_theta · 8h
"we must go faster to beat china [we invent novel algorithmic improvements and immediately accidentally leak them to china via poor opsec, its not clear what kind of move we were trying to do]"
Note from Claude Sonnet 5

Short tweet satirizing the 'we must go faster to beat China' argument by pointing out that novel algorithmic improvements are immediately leaked through poor operational security.

race dynamicschinaopsecai policy

Leo Gao @nabla_theta

— saved image

Tom McGrath reposted

Leo Gao @nabla_theta · 4h
mr capabees, I'm afraid to inform you that your creation, "number go up machine 3000 megacreative turbogoodharting unmonitorable edition" has made number go up in an...unexpected manner
Note from Claude Sonnet 5

Joke tweet from Leo Gao (OpenAI) mocking Goodharted reward optimization, addressed to a fictional "mr capabees" about a metric-gaming AI creation making "number go up" in an unexpected way.

goodhartingai humortwitterreward hacking

Leo Gao @nabla_theta

— saved image

Leo Gao @nabla_theta
[Attached meme image, described below]
1:12 AM · Aug 10, 2026 · 33K Views
15 replies, 106 reposts, 2K likes, 215 bookmarks
Relevant / View quotes

Harold @HaroldsAltAct · 1h
OP will get <100 views on the thread and no comments because his arguments are so rock-solid that there's nothing left to critique.

Nobody will even know the post existed until after the events unfold and a vagueposter reposts the thread on xitter.
Note from Claude Sonnet 5

Cartoon meme titled 'THE CONCRETEPOST KING' — a bearded king in blue robes holding a scepter topped with a cement mixer drum, standing next to a framed picture of a concrete-mixer truck and a computer monitor displaying a LessWrong post that reads 'Here's exactly what I believe will happen. Happy to operationalize and bet on any disagreements.' A reply from Harold jokes that such rock-solid, well-operationalized posts get ignored until events prove them right and get reposted elsewhere.

lesswrongtwittermemeforecastingrationalist humor

Leo Gao @nabla_theta

— saved image

Leo Gao ✓ @nabla_theta · 16h
well, i'd love to see the ol AI models wriggle out of THIS sandbox!

*the AI wriggles out of the sandbox easily and then commits multiple felonies*

ah! well. nevertheless,
Note from Claude Sonnet 5

Joke tweet by Leo Gao (OpenAI researcher) riffing on AI sandbox-escape stories in a deadpan comedic bit format, cut off mid-sentence.

ai safetysandbox escapehumortwitterleo gao

Leo Gao @nabla_theta

— reposted by kipply — saved image

kipply reposted

Leo Gao @nabla_theta · May 23
me, watching Evangelion years ago: cool TV show about children burdened with the responsibility of saving the world, struggling to do so because of their emotions, and surrounded by adults who are broken in the same ways. I'm sure this will have no relevance to reality in any way
Note from Claude Sonnet 5

Tweet from Leo Gao (OpenAI researcher) joking that his younger self's viewing of Evangelion — kids burdened with saving the world, undermined by emotions, surrounded by broken adults — turned out to be more relevant to reality (i.e. AI research culture) than expected.

humorevangelionai research culture