85 subscribers
Go offline with the Player FM app!
Podcasts Worth a Listen
SPONSORED


1 The Southwest’s Wildest Outdoor Art: From Lightning Fields to Sun Tunnels 30:55
How Specialized Models Drive Developer Productivity | Tabnine’s Brandon Jung
Manage episode 441549973 series 2844204
What are the limitations of general large language models, and when should you evaluate more specialized models for your team’s most important use case?
This week, Conor Bronsdon sits down with Brandon Jung, Vice President of Ecosystem at Tabnine, to explore the difference between specialized models and LLMs. Brandon highlights how specialized models outperform LLMs when it comes to specific coding tasks, and how developers can leverage tailored solutions to improve developer productivity and code quality. The conversation covers the importance of data transparency, data origination, cost implications, and regulatory considerations such as the EU's AI Act.
Whether you're a developer looking to boost your productivity or an engineering leader evaluating solutions for your team, this episode offers important context on the next wave of AI solutions
Topics:
- 00:31 Specialized models vs. LLMs
- 01:56 The problems with LLMs and data integrity
- 12:34 Why AGI is further away than we think
- 16:11 Evaluating the right models for your engineering team
- 23:42 Is AI code secure?
- 26:22 How to adjust to work with AI effectively 32:48 Training developers in the new AI world
Links:
- Brandon Jung on LinkedIn
- Brandon Jung (@brandoncjung) / X
- Tabnine (@tabnine) / X
- Tabnine AI code assistant | Private, personalized, protected
- Managing Bot-Generated PRs & Reducing Team Workload by 6%
Support the show:
- Subscribe to our Substack
- Leave us a review
- Subscribe on YouTube
- Follow us on Twitter or LinkedIn
Offers:
225 episodes
Manage episode 441549973 series 2844204
What are the limitations of general large language models, and when should you evaluate more specialized models for your team’s most important use case?
This week, Conor Bronsdon sits down with Brandon Jung, Vice President of Ecosystem at Tabnine, to explore the difference between specialized models and LLMs. Brandon highlights how specialized models outperform LLMs when it comes to specific coding tasks, and how developers can leverage tailored solutions to improve developer productivity and code quality. The conversation covers the importance of data transparency, data origination, cost implications, and regulatory considerations such as the EU's AI Act.
Whether you're a developer looking to boost your productivity or an engineering leader evaluating solutions for your team, this episode offers important context on the next wave of AI solutions
Topics:
- 00:31 Specialized models vs. LLMs
- 01:56 The problems with LLMs and data integrity
- 12:34 Why AGI is further away than we think
- 16:11 Evaluating the right models for your engineering team
- 23:42 Is AI code secure?
- 26:22 How to adjust to work with AI effectively 32:48 Training developers in the new AI world
Links:
- Brandon Jung on LinkedIn
- Brandon Jung (@brandoncjung) / X
- Tabnine (@tabnine) / X
- Tabnine AI code assistant | Private, personalized, protected
- Managing Bot-Generated PRs & Reducing Team Workload by 6%
Support the show:
- Subscribe to our Substack
- Leave us a review
- Subscribe on YouTube
- Follow us on Twitter or LinkedIn
Offers:
225 episodes
All episodes
×
1 Foresight Over Firefighting: Being Proactive in a Reactive World 44:02

1 The End of Specialization? How AI Shapes Modern Dev Teams | Vercel’s Lee Robinson 54:42

1 AI Gets Eyes and Ears | LiveKit’s Russ d’Sa 53:33

1 The Shift to Agent-Driven API Consumption | Speakeasy’s Sagar Batchu 41:17

1 How Marketing Ruined Shift Left | Semgrep’s Tanya Janca 48:52

1 How to Build AI Workflows You Can Trust | Infactory’s Brooke Hartley Moy 43:42

1 Amazon Q and The Future of Autonomous Development | AWS' Adnan Ijaz 42:38

1 Ditch the Ticket Factory Mentality | Cosmic Teacups’ Thanos Diacakis 55:09

1 Will AI Finally Make TDD Practical? | Diffblue’s Animesh Mishra 46:04

1 Can You Buy Your Way to DevSecOps Success? | Arcjet’s David Mytton 48:40

1 Simplifying the AI Stack | IBM's Dr. Maryam Ashoori 46:23

1 Why Are Teams Only Aligned During a Crisis? | CircleCI & MongoDB 1:19:49

1 Can Your AI Strategy Be Future-Proof? | Galileo’s Vikram Chatterji 40:59

1 Why Teams Will Break This Year (and How to Fix Them) | Battery Venture’s Dharmesh Thakker 1:06:25

1 Hunting for a Flywheel | Refactoring’s Luca Rossi 51:38

1 Low-Code Won’t Replace You | Camunda’s Bernd Ruecker 45:30

1 The Need for Speed | 2025 Engineering Benchmarks 31:06

1 Managing Developer Feedback Effectively | Atlassian’s Andrew Boyagi 41:48


1 Season 4 Finale: A Fond Farewell, What’s Next & Would You Rather 40:34

1 Developer Productivity Will Decline in 2025 | Predictions from LinearB’s Ori Keren 38:26

1 From Rockets to Roadmaps: An Engineer's Guide to Product Success | Sift Stack’s Austin Spiegel 28:51

1 From Fear to Function: Rethinking Engineering Processes | Stytch’s Julianna Lamb 25:28

1 Are Only 20% of Devs Happy? | Stack Overflow’s Erin Yepis 45:49

1 Making Sense of Agentic AI | ThoughtWorks Birgitta Boeckeler 47:40

1 Open Source Meets AI | Red Hat's Scott McCarty 45:38

1 Back to First Principles | Productiv CTO Ashish Aggarwal 38:45

1 The Real Measure of Success in Platform Engineering | MassDriver CEO Cory O'Daniel 45:04

1 Transforming Customer Support with AI | DevRev’s Co-founder & CEO Dheeraj Pandey 49:52

1 Observability as a Success Catalyst | Momento’s Co-Founder & CTO Daniela Miao 42:05
Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.