BG2Pod with Brad Gerstner and Bill Gurley
Inside OpenAI Enterprise: Forward Deployed Engineering, GPT-5, and More | BG2 Guest Interview
· Summarized
Key takeaways
- OpenAI is focusing on AI deployment in enterprise settings, aiming to disseminate the benefits of AGI widely across sectors.
- Case studies with T-Mobile, Amgen, and Los Alamos demonstrate the transformative potential of AI on customer support and drug development.
- 95% of AI deployments fail largely due to lack of structural support and proper framework within enterprises.
- GPT-5 showcases significant improvements over previous models, particularly in instruction-following capabilities and reducing hallucinations.
- The advancement of multimodal capabilities suggests a future where AI can seamlessly operate across different media formats.
- Reinforcement fine-tuning enhances model customization, allowing enterprises to leverage unique datasets for specific applications.
- Engagement in tech discussions, like the long/short game, reflects broader trends in market speculation and technology direction.
Summary
OpenAI's Enterprise Mission
The episode dives into OpenAI’s mission beyond ChatGPT, focusing on how they are reshaping enterprise through AI. Sherwin Wu and Olivier Godement explain how OpenAI aims to integrate AI into various industries, helping to maximize the benefits of AGI across different sectors.
Case Studies: Transforming Industries with AI
The podcast showcases specific case studies of OpenAI's work with significant companies like T-Mobile, Amgen, and Los Alamos National Lab. T-Mobile utilizes OpenAI for automating customer support through AI voice technology, Amgen leverages it for accelerating drug development, and OpenAI does a custom deployment for the Los Alamos lab dealing with sensitive data.
Challenges and Failure Rates in AI Deployments
They discuss the challenges within the AI domain, emphasizing a concerning statistic: 95% of AI deployments fail. The conversation reflects on the structural necessities required for successful AI implementations and the importance of scaffolding and infrastructure.
GPT-5 and its Impact
A significant portion of the discussion centers around GPT-5, focusing on its behavioral and performance improvements compared to prior models. Feedback from users highlights strengths like better instruction-following and reduced hallucinations, crucial for enterprise applications.
The Rise of Multimodal AI
The podcast also touches on the development of multimodal capabilities, including the shift from stitched audio systems to real-time APIs that can simultaneously process text, voice, and potentially video, enhancing user experience.
Model Customization and Reinforcement Fine-Tuning
OpenAI’s model customization through reinforcement fine-tuning is highlighted, showing how enterprises can leverage their own datasets to tailor AI models effectively. This approach allows for greater specificity and utility in various fields.
Rapid Fire: Long/Short Picks
In a lighter segment, the hosts and guests share their 'long' and 'short' betting picks in various industries, sparking engaging predictions about trends in AI, eSports, and the future of education.
Sponsors
- T-Mobile Partnership · T-Mobile integrates OpenAI's technology for enhancing customer support with AI voice functionalities.
- Amgen Partnership · OpenAI works with Amgen to expedite drug development processes through AI applications.
- Los Alamos Partnership · OpenAI collaborates with Los Alamos National Lab, implementing AI for research in a secure environment.
- MIT AI Report · Referencing a report on AI deployment failures within enterprises.
Show notes
Open Source bi-weekly convo w/ Bill Gurley and Brad Gerstner on all things tech, markets, investing & capitalism. This week, guest host Altimeter’s Apoorv Agrawal explores how OpenAI is reshaping enterprise with Sherwin Wu, Head of Engineering OpenAI Platform, and Olivier Godement, Head of Product OpenAI Platform. From T-Mobile’s AI voice support to Amgen’s drug breakthroughs to Los Alamos’ air-gapped supercomputer—this episode dives into the real world of AI at scale. Enjoy another episode of BG2!
Timestamps:
(00:00) Intro
(01:50) OpenAI’s Enterprise Mission: Beyond ChatGPT
(06:00) Case Study: T-Mobile <> Voice & Support
(11:30) Case Study: Amgen <> Accelerating Drug Development
(13:45) Case Study: Los Alamos National Lab
(17:00) Why 95% of AI Deployments Fail?
(20:30) Physical vs Digital Autonomy: Scaffolding & Infrastructure
(26:00) GPT-5: Release, Benchmarks vs Behavior
(30:00) GPT-5 Feedback: Instruction Following, Hallucinations, Code Quality
(33:00) Multimodality: Text, Voice, and Video
(35:30) Audio: Realtime API vs Stitched Audio
(38:00) Model Customization & Reinforcement Fine-Tuning (RFT)
(43:00) Rapid Fire: Long/Short Picks
(1:03:00) Highlights and Lowlights @ OpenAI
Show Notes:
T-Mobile Partnership: https://www.t-mobile.com/news/business/t-mobile-launches-intentcx-with-openai
Amgen Partnership: https://openai.com/index/gpt-5-amgen/
Los Alamos Partnership: https://www.lanl.gov/media/news/0130-open-ai
MIT AI Report: https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Business_2025_Report.pdf
Produced by Dan Shevchuk
Music by Yung Spielberg
Available on Apple, Spotify, www.bg2pod.com
Follow:
Brad Gerstner @altcap https://x.com/altcap
Bill Gurley @bgurley https://x.com/bgurley
BG2 Pod @bg2pod https://x.com/BG2Pod
Apoorv Agrawal @apoorv03 https://x.com/apoorv03
Sherwin Wu @sherwinwu https://x.com/sherwinwu
Olivier Godement @oliviergodement https://x.com/oliviergodement
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account