Katie Parrott
PulseAugur coverage of Katie Parrott — every cluster mentioning Katie Parrott across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Author details shift to AI agent orchestration for complex tasks
The author describes a shift in their AI usage from simple prompting to more complex agent orchestration, inspired by a framework for AI adoption. Initially, tasks were handled in single chat threads, but now multiple s…
-
Writers Forge Unique AI Workflows Amidst Debate
Writers are exploring diverse ways to integrate AI into their workflows, with no single approach proving universally effective. Some writers use AI to overcome writer's block by converting research into conversational p…
-
Every explores AI-assisted writing with new 'Compound Writing' plugin
The publication Every is exploring how individuals write with AI, framing it as a collaborative process rather than a question of AI authorship. They are launching a series called "How We Write Now," beginning with a fo…
-
Every builds AI clones of employees to automate expertise
Every, a media company, is developing AI agents to replicate the expertise of its key personnel. Initially, they created KateBench to emulate editor Kate Lee's copyediting skills using GPT-5.6 and historical data. The c…
-
Every conference to explore AI's impact on human work
Every is hosting its first conference, Thesis, on November 5th in Brooklyn, focusing on the future of human work in an automated world. The event will feature leaders from major AI labs and companies discussing AI's cap…
-
New AI Trick Exposes Model Reasoning, Potential Data Leaks
Researchers have developed a method to extract internal reasoning processes from AI models, revealing potential vulnerabilities. This technique can expose personal information, such as passwords and API keys, though thi…
-
OpenAI launches GPT-5.6, but executive departure casts shadow
OpenAI has released its new GPT-5.6 model, available in three tiers: Luna, Terra, and Sol. Early users and critics have praised Sol for its speed, reasoning capabilities, and performance on complex data tasks, with some…
-
GPT-5.6 Sol returns, praised for collaboration but shows benchmark inconsistencies
The AI model GPT-5.6 Sol has returned after a period of government review, with users noting its improved performance and collaborative capabilities. While Fable remains preferred for broad, open-ended tasks, Sol is now…
-
Every details Codex use cases as Anthropic's Fable 5 returns
The AI company Every is highlighting practical use cases for its Codex agentic workspace, emphasizing its versatility and ease of use for non-technical users. Head of consulting Natalia Quintero shared how Codex has bee…
-
US restricts GPT-5.6 Sol access; AI agents expand to knowledge work
OpenAI has released GPT-5.6 Sol, but access is restricted by the U.S. government to about 20 pre-approved companies. This rationing is expected to extend to token access, which will be allocated based on demonstrated re…
-
OpenAI's Codex expands beyond coding with new features and user guides
Every has updated its guide on using OpenAI's Codex for knowledge work, highlighting its expanding capabilities beyond traditional coding. The guide now includes details on new features like Sites and role-specific plug…
-
Anthropic disables Fable 5 model, highlighting AI tool instability · 1 source tracked
Anthropic has disabled its Fable 5 coding model, impacting users like Every who relied on it for development. This sudden shutdown highlights the precariousness of using frontier AI models, as companies or governments c…
-
Every hosts Fable 5 camp to showcase advanced project completion
Every is hosting a two-hour camp to demonstrate how to maximize the use of Anthropic's Fable 5 model for complex projects. The session will cover real-world applications in coding, growth, research, and writing, detaili…
-
Anthropic's Opus 4.8 model tops coding and writing benchmarks
Anthropic has released its latest model, Opus 4.8, which has surpassed previous benchmarks in coding and writing tests, positioning it as the company's most capable model to date. This release marks a significant advanc…
-
Anthropic releases Claude Opus 4.8 with enhanced coding and reasoning
Anthropic has released Claude Opus 4.8, an upgrade to its flagship AI model, boasting significant improvements in coding, reasoning, and reliability. The new version is notably better at identifying code flaws and handl…
-
Every's Guide to Codex: AI Workspace for Knowledge Work
The newsletter "Every" has published a comprehensive guide on leveraging Codex, an AI-powered workspace, for knowledge work. The guide details a five-step process for using Codex, from connecting data sources to compoun…
-
Every pivots AI agents from personal to shared, highlights tacit knowledge extraction
Every's internal AI agents proved unreliable and required too much upkeep, leading to a pivot towards shared, dependable AI coworkers. The publication also highlights techniques for extracting valuable tacit knowledge t…
-
Every pivots AI agent product from individual to team resources
Every, a company focused on the future of work, is pivoting its AI agent product, Plus One. Initially designed as an individual AI assistant for every employee, the product proved more frustrating than efficient due to …