All-In Podcast, September 11, 2026
On the Sep 11, 2026 episode of All-In Podcast, 6 of the 10 words Polymarket listed were said; Parrot’s count agreed with all 10 settlements. Quotes below are at most 25 words each.
UpdatedMarkets
10 words · 6 settled yes · our count agreed on 10 of 10- Polymarket: anyone
Polymarket
backtest The probabilities on settled rows are a walk-forward backtest: the model as of before each event, computed after Parrot went live; they were not published at the time.
| Word | Result | Our count | All speakers | Agrees | Probability | Market |
|---|---|---|---|---|---|---|
| AI 50+ times | Yes | 125 | 125 | ✓ | 75%n=4 from settlement history | – |
| Hundred / Thousand / Million 10+ times | Yes | 40 | 40 | ✓ | 86%n=9 from settlement history | – |
| Anthropic 5+ times | Yes | 28 | 28 | ✓ | 75%n=4 from settlement history | – |
| IPO | Yes | 12 | 12 | ✓ | 85%n=8 from settlement history | – |
| Nvidia | Yes | 1 | 1 | ✓ | 67%n=24 from settlement history | – |
| Yes | 1 | 1 | ✓ | 62%n=4 from settlement history | – | |
| SpaceX 3+ times | No | 1 | 1 | ✓ | 77%n=9 from settlement history | – |
| Smartphone | No | 0 | 0 | ✓ | –new new word, no probability yet | – |
| Microsoft | No | 0 | 0 | ✓ | 44%n=5 from settlement history | – |
| Mark Zuckerberg | No | 0 | 0 | ✓ | 21%n=5 from settlement history | – |
Market prices are mid quotes from Kalshi and Polymarket, shown for context, may be delayed by several minutes and are not a signal. Quotes as of Oct 21, 2026 04:22 UTC.
Transcript
quotes of at most 25 wordsMachine transcript · All-In Podcast podcast audio (All-In), machine transcript · Source · Used to count words; quotes of at most 25 words.
8 matches for “Agent”; 5 quoted, at least 25 words apart.
…the campaign? So what was his goal? And is he a rogue agent? Oh. Is he rogue or he's in coordination? These groups are interested…
…what happens. And along the way, they're going to get speeding tickets or shut down. Agents working together as a swarm is so far removed
…on your phone for free. And you now have an open source AI agent model system that can do all sorts of things for you.
…that they used a reported 130 billion output tokens to do the work between 10,000 agents that were spun up to work with one another.
…this answer. And the work was done across many, many computers, 10,000 agents just means 10,000 applications, running on a computer, talking back and forth…
Where the listed words were said
…I'm going all in. Saks, we have to talk about Anthropic. A researcher just quit over AI fears that he thinks could kill us all.
a tweet go to 150 million views since Elon said he was going to put the cocaine back in Coca-Cola, which I think was the…
…going to get into it. Evan Hubinger, who leads Alignment Science at Anthropic, responded to Jacob. Quote, Jacob is correct here. We really do earnestly…
…both of them did with Playboy, but that was well before the IPO window. And then they published it in the middle of their quiet…
…typical risks. Okay, just explain. The typical risk, Jason, that they would have had would have said competition. NVIDIA may not give us the chips.
Agents: this page as TSV at /api/v1/appearances/all-in-podcast:2026-09-11:podcast_episode · words: /api/v1/brief?appearance=all-in-podcast:2026-09-11:podcast_episode · columnar JSON in #parrot-data · llms.txt · MCP