Featured Story
It's Time To Put Humans Back In The Software
Software engineers have become overreliant on models to build applications, and it's time to put humans more firmly in the loop, the AI Engineer World's Fair was told on Tuesday. The term software engineering was first used in a 1968 NATO conference, which was called to discuss the problems of building large-scale, reliable applications at speed.
News Wire
Bottleneck Resolution Is, In Fact, All the Rage in AI Engineering
The AI Engineer World's Fair is fundamentally a conference for practitioners — devs who need to be productive today. The author explores how the conference discusses practical solutions to real constraints rather than promising frictionless futures.
More Stories
From Harness Engineering to Evals
Despite the AI Engineer World's Fair's vast scale and numerous tracks, a clear pattern emerges when examining what engineers actually deploy to production. The industry is moving past simple chat interfaces and treating large language models like central processing units inside a larger, highly structured software architecture.
AI Isn't Ready to Build Complex Software
Micah Wilde, principal engineer at Cloudflare, offers a sobering reality check on AI coding agents. Wilde is leading the development of a new suite of data platform products and has a front-row seat to both the power and the limitations of generative AI.
Trust but Verify When Using AI for Fixing Security Flaws
AI might seem like a magic bullet for fixing security issues, but it's not that simple, warned Eugene Yan, a member of technical staff at Anthropic, during the newly inaugurated security track at AI Engineer World's Fair. The effectiveness of AI in identifying and resolving vulnerabilities continues to accelerate rapidly.
DevRel in the Age of AI Is a Search for Meaning
AI drives the cost of content creation to zero, making physical, human-created artifacts increasingly valuable as counter-signaling in an age of digital content saturation. Developer relations professionals are reckoning with what authenticity and craft mean when machines can produce anything.
AI Is Going Loopy, But in a Good Way
The AI Engineer World's Fair opening keynote featured co-founder Shawn Wang discussing how AI systems are increasingly using feedback loops. "In the beginning, there was the token, then there was the chat," he noted, explaining that modern AI automation relies heavily on iterative evaluation processes.
Token Town
Most of us don't work for a frontier AI lab. A large fraction of the things we do don't require the biggest, hottest, most token-hungry models. Software orchestration systems now coordinate multiple AI agents in factory-like setups, optimizing for cost and speed.
Visitors Get Some Serious Puppy Love
There may be robots aplenty on the AIE expo floor, but many delegates have been drawn to a more mammalian exhibit. The charity Puppie Love is offering attendees hands-on time with young dogs available for adoption at the event.
Computer Use Is Still the Best Demo in AI. That's a Problem.
Computer use is still the most engaging demo in AI today. Typing a request in plain language and then seeing an agent independently navigate an obtuse website, test code end-to-end, or complete a form feels like witnessing an automated future.
Fable Is Back, Baby.
Fable is back. The Commerce Department announced yesterday it has lifted the export controls it slapped on Anthropic's newest model, and access returns this week. Nobody's spelled out the fine print yet, with early indications pointing toward credit gating and ID verification requirements.
Optimizing for Agents with llms.txt
The AIE World's Fair 2026 website features an llms.txt page designed specifically for AI agents rather than human readers. It follows a standard proposal called the '/llms.txt file,' which provides structured, agent-readable documentation about a site's content and capabilities.
Latest from the Community #AIE and #AI on DEV
Loading posts…


