WEBVTT

1
00:00:10.000 --> 00:00:24.592
Welcome to the Global Advisors A.I Voices podcast. I'm Maya.
Today is Thursday, the twelfth of November 2026.
This is your morning catch-up on A.I. Please like and follow the show for your daily A.I update.

2
00:00:26.641 --> 00:00:39.569
Anthropic is expanding its office suite with new tools for collaboration. The company launched Claude Whiteboards and Claude Sheets in beta, while making its analytics tool, now called Claude Data, generally available.

3
00:00:39.919 --> 00:00:58.970
These products are available on paid plans across web, desktop, and mobile, keeping boards, sheets, and documents inside Claude during collaboration. Whiteboards offers a real-time canvas where Claude can turn discussions into timelines with owners and dates, or convert boards into presentations.

4
00:00:59.320 --> 00:01:21.784
Claude Sheets can generate spreadsheets with tabs, formulas, and formatting from prompts, with options to export to Excel. Claude Data builds on the previous Dashboards beta, adding governance features and live sharing. Administrative defaults vary by plan, with Team plans having all three products on by default, while Enterprise plans start with Whiteboards and Sheets off.

5
00:01:24.183 --> 00:01:45.346
In a recent breakdown of Alex Hormozi's A.I strategies, the video from Nate Herk | A.I Automation reports that his media team tripled their output in just one month without increasing headcount. The video explains that A.I prompts handled thirty to fifty percent of the workload, allowing existing employees to absorb the extra volume.

6
00:01:45.696 --> 00:02:03.402
Alex Hormozi argues that by breaking editor roles into specific workflows, A.I allows one person to do the work of multiple people. The video illustrates this with an example where A.I reads transcripts to find high-tension moments and removes filler words like 'ums' and 'ahs'.

7
00:02:05.801 --> 00:02:25.961
In a video from Nate Herk | A.I Automation, the source video reports that Alex Hormozi froze his team's A.I budgets because revenue remained flat despite high spending per employee. This decision highlights a critical disconnect between investment and return when automation is applied without strategic focus.

8
00:02:26.311 --> 00:02:46.023
The source video notes that Hormozi identifies a recurring three hundred and fifty thousand dollar mistake where businesses automate processes that are not actual constraints. By targeting non-priority tasks, companies waste resources on solutions that do not address the primary bottlenecks holding their growth back.

9
00:02:46.373 --> 00:03:02.181
According to the source video, Hormozi advises aiming A.I at the single real constraint of the business rather than using it everywhere indiscriminately. This approach suggests that without a clear bottleneck, A.I spending often fails to drive meaningful growth.

10
00:03:04.581 --> 00:03:15.973
OpenAI's quarterly revenue reportedly crossed ten billion dollars for the first time. Bloomberg attributes this milestone to strong demand for the company's recent A.I models.

11
00:03:16.323 --> 00:03:25.304
This ten billion dollar sales figure represents an almost fifty percent jump from the six point seven billion dollars recorded in the second quarter.

12
00:03:27.703 --> 00:03:43.255
In a showcase demonstration, Anthropic reported that its Fable 5.2 model coordinated over one thousand sub-agents to build a working operating system from scratch. This included core components, drivers, and a login screen.

13
00:03:43.605 --> 00:04:04.384
SiliconANGLE confirms that an Anthropic engineer tested Fable 5.2 by asking it to build an operating system, resulting in one thousand agents completing the task. According to SiliconANGLE, the generated operating system is capable of running on a laptop, offers network access, and features a Claude sidebar.

14
00:04:06.783 --> 00:04:25.279
The A.I Daily Brief reports that Anthropic's new Fable 5.2 model demonstrated significant leads in coding benchmarks. On the Frontier Code test, Fable 5.2 scored four points higher than GPT-6 Astra and three and a half points higher than Opus 5.5.

15
00:04:25.629 --> 00:04:38.344
These margins suggest a notable performance gap in agentic coding tasks, positioning Fable 5.2 as a strong contender for developers seeking high-precision code generation capabilities.

16
00:04:40.743 --> 00:04:54.545
France has unveiled the Paris Call for A.I Safety and Security. OpenAI, Anthropic, Microsoft, and Mistral are among ten A.I companies that signed the new declaration on advanced A.I model safety.

17
00:04:54.895 --> 00:05:11.877
Signatories committed to developing fail-safe mechanisms to shut down A.I models, including during training and internal use. The commitments also include providing clearer information about system capabilities and allowing qualified independent experts to test models.

18
00:05:12.227 --> 00:05:24.451
Several nations, including France, Canada, Finland, Norway, the Netherlands, and Bahrain, signed the declaration. However, major tech companies Google and Meta, along with China, did not sign.

19
00:05:26.850 --> 00:05:42.956
Google announced the availability of Gemini 4 Carbon to developers, enterprises, scientists, and consumers. The company describes it as its strongest model, featuring frontier performance in cybersecurity and long-horizon agentic workflows.

20
00:05:43.306 --> 00:06:05.621
Google notes that while Gemini 4 Argon remains suitable for most software engineering, Carbon is designed for tasks testing the limits of model intelligence, such as complex debugging and open-ended scientific research. The model is rolling out via the Gemini API in Google A.I Studio and Gemini for business for all paying developers and enterprises.

21
00:06:05.971 --> 00:06:24.190
Google is also previewing a 'swarm' feature in its Antigravity platform, allowing users to turn a single prompt into a coordinated team of agents. Gemini 4 Carbon is priced at two dollars per million input tokens and ten dollars per million output tokens as an introductory price.

22
00:06:26.589 --> 00:06:49.010
OpenAI has launched a beta program allowing businesses to claim verified profiles in ChatGPT and deploy A.I agents to answer customer questions. Eligible United States online retailers and service businesses can publish these Business Agents, which can also serve as destinations for ChatGPT ads in limited testing.

23
00:06:49.360 --> 00:07:07.835
The feature provides marketing teams a way to correct information and measure traffic from a service reaching one point two billion weekly users. Benji Shomair, OpenAI's VP of Monetization, notes that profiles and agents are free to claim at launch, though future charging is possible.

24
00:07:08.185 --> 00:07:31.801
The Business Hub dashboard shows aggregate activity like website clicks and mentions over the past twenty-eight days. OpenAI states it does not share user conversations with businesses, and insights are only reported after meeting minimum thresholds. A blue check mark indicates a claimed profile but does not guarantee comprehensive validation of all business-supplied details.

25
00:07:34.200 --> 00:07:53.272
On The MAD Podcast with Matt Turck, Nathan Benaich describes using an A.I agent to conduct twelve interviews across the United States, India, Europe, Germany, and France in two and a half days. He had a tight deadline to provide an answer to a company, and the first day resulted in interviews from senior people.

26
00:07:53.622 --> 00:08:14.124
Benaich explains that the A.I agent analyzed initial transcripts to identify new question streams, retuned the interview questions to coax specific answers, and relaunched the survey. This iterative refinement allowed the agent to adapt its approach based on early responses, significantly accelerating the research process.

27
00:08:16.523 --> 00:08:33.333
The Financial Times reports that Mittelstand companies' accumulated experience could provide them with an edge in A.I. Manufacturers hope that years of data will help train A.I tools, as illustrated by Safelog robots at a Mercedes-Benz factory.

28
00:08:33.683 --> 00:08:46.505
Manufacturers are looking to use historical data to train A.I tools, leveraging their long-standing operational records to build specialized models that competitors may lack the data to replicate.

29
00:08:48.904 --> 00:09:04.712
The Wall Street Journal reports that Nvidia's board is meeting as soon as Wednesday to determine C E O Jensen Huang's future. Huang admitted to an extramarital affair with a woman purported by United States intelligence to be a Chinese spy.

30
00:09:05.062 --> 00:09:14.192
Nvidia stock fell about eight percent in after-hours trading on Wednesday. The company's stock is down about eleven percent in the past five days.

31
00:09:14.542 --> 00:09:28.985
Ann Lipton notes that the company has not had an obvious successor or a succession plan. Bloomberg reports that Nvidia is working with an outside firm to identify candidates that could potentially replace Huang as C E O.

32
00:09:29.335 --> 00:09:45.783
That's A.I Voices for today. I'm Maya. Thanks for listening.
Follow the show on Spotify, YouTube, Apple Podcasts, Amazon Music, or your favourite podcast platform, and explore the original voices and sources in the episode notes. See you tomorrow.