LLMs can now cite their sources
Bill Doerrfeld | April 9, 2025
My latest post on The New Stack reveals how researchers pinpoint the exact sources behind chatbot responses.
Today the Allen Institute for Artificial Intelligence (Ai2) unveiled OLMoTrace — a seemingly minor feature with major implications for AI verifiability.
Check out my post on The New Stack, which dives into the technology that is allowing LLMs to cite the exact source behind chatbot responses.
I was excited to see this since LLMs have struggled with transparency. I sense this could set a precedent for other chatbots to embed similar traceability.
Featured image credit: natalie nedelmann
For CIO.com, leading executives shared with me how they're actively utilizing agentic AI to enhance core business workflows.
Developer productivity metrics are useless if they're just sitting in dashboards. So, how can we use them to direct positive, real-world action?
What leads to a higher revenue per engineer? New benchmarking from DX reveals how areas like R&D spend, org size, and growth rate move the needle.
The Kubernetes ecosystem has exploded with managed platforms tailored to multi-cloud, edge, on-prem, and regional deployments.
Some internal projects are too good to stay hidden. For DirectorPlus, Spotify's Pia Nilsson shares how to identify and externalize internal platforms — like they did with Backstage.
My latest feature for InfoWorld looks into the gaps surrounding AI-generated code and what leaders believe we need to improve the status quo.
New research shows LLMs outperform humans in software requirements engineering, reducing weeks of work to seconds while improving completeness by 10.2%.
Containers are designed to be isolated—that's great for security but tricky for networking. My feature with InfoWorld explores how eBPF is evolving container networking.
I recently synced with Camden Swita, Head of AI and ML Innovation at New Relic, to see how software engineers are implementing agentic AI in practice.
The 2nd annual code quality report from GitClear found 10x more duplicated code than two years ago and fewer signs of code reuse than ever before.
