StackOverflow blog

A brief summary of language model finetuning

There are a ton of different ways to finetune a language model. Here's a (brief) summary of language model finetuning, the various approaches that exist, their purpose, and what we know about how they work. https://stackoverflow.blog/2025/10/31/a-brief-summary-of-language-model-finetuning/

Life in the Fastlane: SDK tools built with developers in mind


On this sponsored episode, Ben and Ryan talk to Sunny Patel, Staff Software Engineer at PayPal, and Kyle Prinsloo, a developer and a PayPal partner, about all the ways that Fastlane by PayPal makes developers’ lives easier. They explore the needs that both merchants and consumers have for creating a seamless checkout experience, the importance of reducing friction in payment processes, and how documentation can directly assist the integration experience. https://stackoverflow.blog/2024/10/30/pay

How can you get your kids into coding? We asked an 8-year-old.

Ben welcomes Ricky Robinett, VP of Developer Relations and Community at Cloudflare, and his eight-year-old daughter Fay for a chat about how AI tools are helping new developers get started and how to encourage your kids to try coding. https://stackoverflow.blog/2024/10/29/how-can-you-get-your-kids-into-coding-we-asked-an-8-year-old/

Tragedy of the (data) commons

Ben chats with Shayne Longpre and Robert Mahari of the Data Provenance Initiative about what GenAI means for the data commons. They discuss the decline of public datasets, the complexities of fair use in AI training, the challenges researchers face in accessing data, potential applications for synthetic data, and the evolving legal landscape surrounding AI and copyright. https://stackoverflow.blog/2024/10/25/tragedy-of-the-data-commons/

How to improve the developer experience in today’s ecommerce world

We walk through the process of designing an SDK that makes it easy for developers to integrate new technology into their e-commerce stack and is flexible enough to serve the needs of small businesses and large enterprises. https://stackoverflow.blog/2024/10/23/improve-developer-experience-ecommerce-fastlane-paypal-sponsored/

Enterprise 2024.7: Empower your subject matter experts to contribute

This release introduces Subject Matter Expert (SME) Auto-Assign to the Stack Overflow for Teams experience so expert knowledge is automatically captured, verified, and distributed to users. https://stackoverflow.blog/2024/10/23/empower-subject-matter-experts-to-contribute/

CEO Update: Building trust in AI is key to a thriving knowledge ecosystem

The internet and its business models are changing. Stack Overflow has been at the forefront, helping to shape the future of the web. https://stackoverflow.blog/2024/10/22/stack-overflow-ceo-update-first-half-1h-2024/

The new pair programming: an AI agent that cleans your code as you write

Ben welcomes Sonar CEO Tariq Shaukat for a conversation about AI coding tools’ potential to boost developer productivity—and how to balance those potential gains against code quality and security concerns. They talk about Sonar’s origins as an open-source code quality tool, the excellent reasons to embrace a “clean as you code” philosophy, and how to determine where AI coding tools can be helpful and where they can’t (yet). https://stackoverflow.blog/2024/10/22/the-new-pair-programming-an-ai-age

How API security is evolving for the GenAI era

Ben Popper chats with Keith Babo, Head of Product at Solo.io, about how the API security landscape is changing in the era of GenAI. They talk through the role of governance in AI, the importance of data protection, and the role API gateways play in enhancing security and functionality. Keith shares his insights on retrieval-augmented generation (RAG) systems, protecting PII, and the necessity of human-in-the-loop AI development. https://stackoverflow.blog/2024/10/18/how-api-security-is-evolving-

Brain Drain: David vs Goliath

There are worries that GenAI systems may run out of fresh data as they scale. Synthetic data is an option, but using AI-generated data to train AI can degrade the model's performance. There may be a better solution. Can data quality overcome a loss of data quantity? https://stackoverflow.blog/2024/10/17/training-data-scarcity-synthetic-quality-model-genai-ai/


Membri



Ricerca