Tech

Exa AI Research Blog

Discover the latest in AI research and semantic search technology on the Exa blog. Learn how our neural network search engine provides high-quality web data for AI applications

Exa AI Research Blog

Discover the latest in AI research and semantic search technology on the Exa blog. Learn how our neural network search engine provides high-quality web data for AI applications

I built an 11-tab financial model in 10 minutes + the prompting guide that makes it repeatable

This morning I built an eleven-tab financial model in ten minutes. Sensitivity analysis, opportunity cost comparisons against S&P 500 returns, risk quantification, market data by zip code, cash flow projections—the whole apparatus. Two weeks of work compressed into the time it takes to make coffee. Norway’s sovereign wealth fund reports saving 213,000 hours with the same tool. This is not incremental improvement. This is a phase change in what knowledge work means.

Executive Briefing: Why 95% of AI Deployments Stall Before Production (And What To Do About It)

The productivity gains from AI are documented. The tools are deployed. And yet most organizations aren’t capturing the value—because they’ve invested in the wrong layer.

My honest field notes on scaling agents past the demo phase + 6 rules from teams running hundreds

A December 2025 study from Google and MIT found something I wasn’t expecting: adding more agents to a system can make it perform worse. Not diminishing returns—actual degradation. The researchers documented configurations where more agents produced worse outcomes than fewer—a finding that directly challenges the field’s working assumption that adding agents means adding capability.

The Specification Gap: Why Your AI Produces Impressive-Looking Output With Fundamental Problems + The Prompt Kit To Help You Fix It

Cursor ran a fleet of agents for close to a week in January 2026, and found GPT-5.2 best for extended autonomous work. When the experiment finished, the system had generated over a million lines of Rust code across a thousand files and built a browser rendering engine—HTML and CSS parsing, cascade, layout, text pipeline, paint, and JavaScript integration. The FastRender repo describes itself as “under heavy development,” and Simon Willison actually ran it and posted screenshots: it kind of works.

My honest take on what AI is structurally better at than your best architects (and where it still falls short)

AI might be better at software architecture than humans.

Why High Agency is a Non-Negotiable in 2026 (especially if you're entry level) + 10 Prompts to Build Your Own Ladder

Entry-level hiring at major technology companies has collapsed by more than fifty percent since 2019, according to SignalFire’s analysis of new grad hiring at large tech firms. Globally, entry-level job postings—roles requiring zero to two years of experience—declined sharply through 2024 and into 2025, per Randstad data reported by the World Economic Forum. The unemployment rate for recent college graduates sits at 5.3 percent as of Q3 2025—above the 4.4 percent overall unemployment rate reported by the Bureau of Labor Statistics in December 2025, according to New York Fed and BLS data.

5 AI Stories, 1 Pattern—xAI, Apple, Davos: Who's Locking In Positions (and Who's Too Late)

This week, two leading AGI-lab CEOs sat on the same stage and warned: timelines may be shorter than the public expects, and entry-level white-collar roles could be hit hard within years.

Terminally online Mistral Vibe.

Today, we're releasing Mistral Vibe 2.0—a major upgrade to our terminal-native coding agent, powered by the state-of-the-art Devstral 2 model family. Build custom subagents, clarify before you execute, load skills with slash commands, and configure your own workflows to match how you work.

The Universities Space Research Association Applies Segment Anything Model for Responding to Flood Emergencies

The Universities Space Research Association and Meta are collaborating to help support water observing systems set up by the U.S. Geological Survey.

How DINO and SAM are Helping Modernize Essential Medical Triage Practices

By leveraging advanced AI models, teams at the University of Pennsylvania are aiming to bring cutting-edge automation to emergency response.