Ep. #71, Evaluating LLM-based Apps with Shir Chorev of Deepchecks

In Episode 71 of o11ycast, Jessica Kerr and Austin Parker sit down with Shir Chorev to delve into the nuances of incorporating Generative AI into applications and testing the outcomes. Shir shares her journey from a data scientist to founding Deepchecks, driven by her vision to enhance the quality and reliability of machine learning and AI in real-world scenarios. Gain valuable insights on how LLMs are reshaping the development landscape, making advanced projects more accessible, and strategies for mitigating adversarial use cases. Whether you're in DevOps, infrastructure, or just passionate about AI, this episode is packed with expert advice and cutting-edge information.

In episode 11 of How It's Tested, Eden Full Goh sits down with Yechezkel Rabinovich of Groundcover to delve into the evolving landscape of observability. They explore the high costs of early observability measures and how Groundcover aims to make these processes more accessible and affordable. Yechezkel shares insights on eBPF, the rise of Flora, and the impact of using an open-source stack. Discover how Groundcover's innovative testing methods and commitment to metrics are reshaping engineering practices and what the future holds for this pioneering platform.

In episode 13 of Generationship, Rachel Chalmers and Archita Mandal explore the transformative effects of generative AI across creative industries. They explore the ways GenAI boosts productivity, democratizes creativity by lowering production costs, and is revolutionizing the film industry.Archita continues to unpack her journey as a founder and CEO, sharing insights on the customer discovery process, product-market fit, and the challenges early-stage startups face, offering a unique perspective on the investor side of AI, including the hype and realities of fundraising. Join Rachel and Archita for a deep dive into the societal impacts of AI and its role as a co-pilot for innovation and storytelling.

In episode 12 of Generationship, Rachel Chalmers sits down with Lilly Ryan, an Information Security specialist based in Australia, to delve into the intricate world of generative AI and its potential misuses. Together they unpack the nuances of prompt injection and other adversarial attacks, shedding light on the dark side of AI technology. They discuss countermeasures to technological colonialism, strategies for maintaining a human-centered web, and the evolving role of AI in our workplaces. Tune in to explore the fascinating intersections of security, technology, and human interaction in the age of AI.

In episode 70 of o11ycast, Jess and Martin speak with Dan Gomez Blanco of Skyscanner. Dan shares his expertise on evangelizing better observability practices at Skyscanner and offers insights from his experience on the OpenTelemetry governance committee. Discover how observability can minimize organizational costs, the future of auto-instrumentation, and valuable advice on detecting and avoiding over-instrumentation. Plus, learn about the importance of tail sampling and OpenTelemetry’s semantic conventions.

In episode 11 of Generationship, Rachel is joined by Adio Dinika of The DAIR Institute to discuss ghost workers. This talk examines the challenges faced by platform laborers around the world, including unfair compensation, job insecurity, and data rights violations. Additionally, they explore the community-rooted AI research that's being done at The DAIR Institute.

In episode 147 of Jamstack Radio, Brian speaks with Chris Stolt and Ben Burkert of Anchor about securing local development environments. This talk explores dev/prod parity and how Anchor’s taking​​​ ​a ​developer-​first ​approach to ​addressing ​the ​pains ​of ​internal ​TLS.

In episode 10 of Generationship, Rachel Chalmers and Dr. Marie Oldfield explore ethical benchmarks in AI. This conversation sheds light on professional accreditation for AI practitioners and offers unique insights on mitigating societal risks while building better AI models. Additionally, Marie shares lessons learned from her expansive career journey across Government, Defense, Legal, and Tech.

In episode 146 of Jamstack Radio, Brian Douglas speaks with Brian Levine of Yetto about customer support. Together they explore the pain points that lead small companies to adopt help desks or support tech stacks, as well as solutions for bolstering customer success like tools and hiring practices.

In episode 41 of The Kubelist Podcast, Marc and Benjie speak with Lukas Gentele of Loft Labs about vCluster. Together they dive deep on how vCluster works and some of the new use cases that the project enables when running on larger, more mature enterprises. This technical discussion explores the problems Lucas and his team set out to solve when they created vCluster.