Angie Jones
PulseAugur coverage of Angie Jones — every cluster mentioning Angie Jones across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Open vs. Proprietary LLMs: Control, Cost, and Customization Drive Choice
The choice between open-weight and proprietary large language models depends on specific needs, with open models offering greater control over training, data usage, and deployment for tasks requiring customization or on…
-
Block rolls out internal AI agent Goose to 12,000 employees via phased rollout
Block, the company behind Square and Cash App, has successfully rolled out an internal AI agent called Goose to its 12,000 employees by implementing a phased, cohort-based approach. The rollout prioritized engineering t…
-
Goose implements AI contribution guidelines to manage open-source influx
Angie Jones and her team at Goose developed a strategy to manage the influx of AI-generated contributions to their open-source project. They established clear guidelines and utilized AI agents to assist in processing th…
-
Angie Jones discusses AI in keynote at All Things Open
Angie Jones delivered a keynote address at the All Things Open conference, focusing on the topic of Artificial Intelligence. The presentation was shared via a link to her personal tech blog.
-
Block tightens AI security with allow-lists and hidden character scans
Block, a financial services company, is implementing strict security measures for its internal AI agent, Goose. To prevent employees from installing unauthorized AI servers, Block uses an allow-list within the agent cli…
-
AI agents need clear tool descriptions to avoid errors, experts say
Writing clear and unambiguous tool descriptions is crucial for AI agents to correctly select and utilize tools, according to insights from Chip Huyen and Angie Jones. Huyen emphasizes that descriptions must clearly indi…
-
Context over MCP series concludes with lessons on agent context delivery
The author reflects on a series of posts about "Context over MCP," a system designed to provide AI agents with project context even when they lack a traditional working directory. Key lessons learned include the need to…
-
AI testing needs new approach beyond traditional pyramid, says expert
Angie Jones posits that the standard testing pyramid is unsuitable for AI systems due to their non-deterministic outputs. She suggests that testing should shift from verifying exact responses to evaluating an AI agent's…
-
OpenAI advances AI research with new benchmarks and infrastructure policies
OpenAI has released several updates and research initiatives, including a study on AI's impact on freelance work, a new system called Control Room for monitoring and stopping AI workloads, and a benchmark called BioBasi…