From search trees to neural nets, a deep dive into natural language processing
The Stack Overflow Podcast23 Jun 2021

From search trees to neural nets, a deep dive into natural language processing

We chatted with three guests:

Miguel Jetté: Head of AI R&D

Josh Dong: AI Engineering Manager

Jenny Drexler: Senior Speech Scientist

When Jette was studying mathematics in the early 2000s, his focus was on computational biology, and more specifically, phylogenetic trees, and DNA sequences. He wanted to understand the evolution of certain traits and the forces that explain why our bones are a certain length or our brains a certain size. As it turned out, the algorithms and techniques he learned in this field mapped very well to the emerging discipline of automatic speech recognition, or ASR.

During this period, Montreal was emerging as a hotbed for artificial intelligence, and Jette found himself working for Nuance, the company behind the original implementation of Siri. That experience led him to several positions in the world of speech recognition, and he eventually landed at Rev, where he founded the company’s AI department.

Jette describes Rev as an “Uber for Transcription.” Anyone can sign up for the platform and earn money by listening to audio submitted by clients and transcribing the speech into text. This means the company has a tremendous dataset of raw audio that has been annotated by human beings and, in many cases, assessed a second time by the client. For someone looking to build an AI system that mastered the domain of speech to text, this was a goldmine.

Jette built the earliest version of Rev’s AI, but it was up to our second guest, Josh Dong, to productize and scale that system. He helped the department transition from older technologies like Perl to more popular languages like Python. He also focused on practical concerns like modularity and reusable components. To combine machine learning and DevOps, Dong added Docker containers and a testing pipeline. If you’re interested in the nuts and bolts of keeping a system like Rev’s running at tremendous scale, you’ll want to check out this part of the show.

We also explore some of the fascinating future and promise this technology holds in our time with Jenny Drexler. She explains how Rev is moving from a hybrid model—one that combines Jette’s older statistical techniques with Dong’s newer machine learning approach—to a new system that will be ML from end-to-end. This will open up the door for powerful applications, like a single system that can convert speech text across multiple languages in a single piece of audio.

“One of the things that's really cool about these end to end models is that basically, whatever data you have, it can learn to handle it. So a very similar architecture can do sequence to sequence learning with different kinds of sequences. The model architecture that you might use for speech recognition can actually look very similar to what you might use for translation. And you can use that same architecture, to say, feed in audio in lots of different languages and be able to do transcription for any of them within one model. It's much harder with the hybrid models to sort of put all the right pieces together to make that happen,” explains Drexler.

If you’re interested in learning more about the past, present, and future of artificial intelligence that can understand our spoken language and learn how to respond, check out the full episode. If you want to learn more about Rev or check out some of the positions they have open, you can find their careers page here.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Episoder(896)

Revealing the unknown unknowns in your software

Revealing the unknown unknowns in your software

Ryan welcomes Nic Benders to discuss the complexity and abstraction crisis in software development, the importance of going beyond observability into understandability, and demystifying AI's opacity for understanding and control.Episode notes:New Relic is a full-stack observability platform that helps engineers plan, build, deploy, and run software. Read their 2025 observability forecast. Connect with Nic on Linkedin or email him at nic@newrelic.com.Congratulations to user Yochai Timmer for winning a Populist badge on their answer to Reader/Writer Locks in C++. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

7 Nov 31min

To write secure code, be less gullible than your AI

To write secure code, be less gullible than your AI

Ryan is joined by Greg Foster, CTO of Graphite, to explore how much we should trust AI-generated code to be secure, the importance of tooling in ensuring code security whether it’s AI-assisted or not, and the need for context and readability for humans in AI code.Episode notes:Graphite is an AI code review platform that helps you get context on code changes, fix CI failures, and improve your PRs right from your PR page. Connect with Greg on LinkedIn and keep up with Graphite on their Twitter. This week’s shoutout goes to user xerad, who won an Investor badge by dropping a bounty on the question How to specify x64 emulation flag (EC_CODE) for shared memory sections for ARM64 Windows?.TRANSCRIPTSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

4 Nov 28min

Vibe coding needs a spec, too

Vibe coding needs a spec, too

Ryan talks with Deepak Singh, VP of Developer Agents and Experiences at AWS and lead at Kiro, about spec-driven development in a vibe coding world. They explore how AI tools have evolved from autocomplete to sophisticated agents that can write code based off of just specs, and how AWS has pioneered spec-driven development through their Kiro agent. Episode notes:Kiro is AWS’ AI IDE that brings structure to AI coding with spec-driven development. Connect with Deepak on the Kiro Discord server and read more about spec-driven development on The New Stack. We last spoke to Deepak Singh in March about how enterprise-ready agents are.Congratulations to user Whymarrh for winning a Populist badge on their answer to Git commits are duplicated in the same branch after doing a rebase. Learn more about the future of software engineering in the AI age on November 3rd, when our CEO, Prashanth Chandrasekar, speaks at a virtual OpenAI Forum.TRANSCRIPTSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

31 Okt 26min

Craft and quality beat speed and scale, with or without agents

Craft and quality beat speed and scale, with or without agents

Ryan welcomes Tom Moor, head of engineering at Linear, to discuss AI agents’ mixed results for productivity in the development lifecycle, the importance of context for maximizing agents’ effectiveness, and the role that junior developers need to take in a world increasingly driven by AI.Episode notes:Linear is a tool for planning and building products that streamline issues, projects, and product roadmaps.Connect with Tom on Twitter. This episode’s shoutout goes to user ozz, who won a Populist badge for their answer to Column width not working in DataTables bootstrap.TRANSCRIPTSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

28 Okt 27min

Your runbooks are obsolete in the age of agents

Your runbooks are obsolete in the age of agents

Ryan is joined by Spiros Xanthos, CEO and founder of Resolve AI, to talk about the future of AI agents in incident management and troubleshooting, the challenges of maintaining complex software systems with traditional runbooks, and the changing role of developers in an AI-driven world.Episode notes:Resolve AI is building agents to help you troubleshoot alerts, manage incidents, and run your production systems. Connect with Spiros on Linkedin or email him at spiros@resolve.ai. Congrats to user larsks for winning a Stellar Answer badge for their answer to How do I get into a Docker container's shell?.TRANSCRIPTSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

24 Okt 24min

What leaders need to know from the 2025 Stack Overflow Developer Survey

What leaders need to know from the 2025 Stack Overflow Developer Survey

In this episode of Leaders of Code, Eira May, B2B Editor at Stack Overflow, and Natalie Rotnov, Senior Product Marketing Manager for the Enterprise Product Suite at Stack Overflow, unpack the key takeaways from the 2025 Developer Survey for tech and business leaders. The discussion focuses on the evolving developer relationship with AI, the continued struggle with tool sprawl, and actionable recommendations for leaders looking to deliver value and improve developer experience.The discussion covers critical findings for tech leaders:The decline in developer trust in AI is linked to two main frustrations: solutions that are "almost right, but not quite" and the time wasted debugging AI-generated code.Human connection and community validation remain vital: 80% of developers still visit Stack Overflow regularly, and the number of "advanced questions" on the public platform has doubled since 2023, underscoring AI’s limitations when it comes to complex, context-dependent questions.Tool sprawl continues, as most developers use 6–10 tools, suggesting that AI tends to complicate rather than simplify workflows.Notes:Explore key insights from the 2025 Stack Overflow Developer Survey, consolidated into an executive-ready summary. Connect with Natalie Rotnov on LinkedIn.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

23 Okt 31min

Open source is giving you choices with your agent systems

Open source is giving you choices with your agent systems

Ryan welcomes John Dickerson, CEO of Mozilla.ai, to talk about the evolving landscape of AI agents, the role of open source in keeping the tech ecosystem healthy, the challenges OS communities have faced with the rise of AI, and the implications of data privacy and user choice in the age of multi-agent AI systems. Episode notes:Mozilla.ai is building the agent platform that helps organizations safely automate real work with AI agents. Connect with John on Linkedin or email him at john@mozilla.ai. Congrats to Populist badge winner Philipp Merkle, who won it for their answer to How to set the -Xmx when start running a jar file?.TRANSCRIPTSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

21 Okt 26min

Why rent a cloud when you can build one?

Why rent a cloud when you can build one?

Andrei Kvapil, founder of Ænix and core developer of Cozystack, joins Ryan to dive into what it takes to build a cloud from scratch, the intricacies of Kubernetes and virtualization, and how open-source has made digital sovereignty possible. Episode notes:Cozystack is a Kubernetes-based framework for building a private cloud environment.Connect with Andrei on Linkedin. Today’s shoutout goes to user Adam for winning a Populist badge for their answer to Regex replace text but exclude when text is between specific tag. TRANSCRIPTSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

17 Okt 29min

Populært innen Business og økonomi

stopp-verden
lydartikler-fra-aftenposten
dine-penger-pengeradet
e24-podden
rss-penger-polser-og-politikk
rss-borsmorgen-okonominyhetene
kommentarer-fra-aftenposten
pengepodden-2
finansredaksjonen
utbytte
pengesnakk
tid-er-penger-en-podcast-med-peter-warren
morgenkaffen-med-finansavisen
rss-markedspuls-2
stormkast-med-valebrokk-stordalen
livet-pa-veien-med-jan-erik-larssen
rss-investering-gjort-enkelt
rss-fri-kontantstrom
okonomiamatorene
paretopodden