A
ARC-AGI-3
TopicHeard in 12 episodes across 8 shows since Jul 2026
A purported third-generation benchmark in the Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) series, intended to evaluate AI systems on novel abstract reasoning and generalization tasks. The excerpt’s claims about a 99–99.9% score and a system called “Astra” cannot be independently verified from the provided context.
Discussed inBusiness100%
Episodes
12
across 8 shows
This week
0
episodes on 0 shows
Share of the conversation
Mentions of ARC-AGI-3 per 1,000 mentions of anything, 7-day rolling, across the podcasts PodLume Trends follows.
Show the data
| Day | Share (7-day) | Mentions |
|---|---|---|
| Sep 2 | 0.01‰ | 1 |
| Sep 3 | 0.05‰ | 4 |
| Sep 4 | 0.09‰ | 4 |
| Sep 5 | 0.10‰ | 1 |
| Sep 8 | 0.12‰ | 1 |
| Oct 2 | 0.01‰ | 1 |
| Nov 19 | 0.01‰ | 1 |
Email alert
Email me when ARC-AGI-3 comes up on a podcast
One email a week at most, with the new episodes that mention ARC-AGI-3. Free, no account needed, unsubscribe in one click.
Episodes
12 episodes featuring ARC-AGI-3, newest first
- Nov 19, 2026
Anthropic’s IPO could remake San Francisco’s startup economyMoonshots with Peter DiamandisNov 19, 2026 - Oct 2, 2026
Alex Zhang argues better harnesses could unlock hidden AI capabilityLatent Space: The AI Engineer PodcastOct 2, 2026 - Sep 8, 2026
GPT-6 Astra brings AI job disruption into viewThe Artificial Intelligence ShowSep 8, 2026 - Sep 5, 2026
Next-generation AI scaling and affordable autonomous transport reshape the global economyMoonshots with Peter DiamandisSep 5, 2026 - Sep 4, 2026
GPT-6 Astra tests AI’s reach as infrastructure shows its fragilityThe AI PodcastSep 4, 2026 - Sep 4, 2026
OpenAI’s Astra raises the stakes for agentic AITech Brew Ride HomeSep 4, 2026