A report from VentureBeat traces the rise of AI-related software incidents, citing that 45% of AI-generated code changes require debugging in production and the 2025 DORA report found a 10% increase i…
Andrew Ng, founder of Coursera and lecturer at Stanford, identified four essential AI development skills based on an analysis of more than 10,000 job postings and interviews with experts, hiring manag…
Junior software developer employment in the U.S. has declined for 33 consecutive months, with a Stanford study using ADP payroll data finding entry-level employment in AI-exposed fields dropped roughl…
Warren Buffett's advice that communication skills are the best way to improve oneself has become more valuable in the AI era, as AI can generate content but cannot earn trust or inspire commitment. Bu…
Terminal-bench, a collection of harbor-native benchmarks from the Harbor Framework, enables agent makers to quantify their agents' terminal mastery, with terminal-bench@2.1 leaderboard showing task re…
A new pejorative term, 'meat proxy,' coined by developer Niklas Gruhn and popularized by Simon Willison, describes people who forward AI-generated responses without reading or verifying them. The term…
LinkedIn's principal AI researcher Praveen Bodigutla said the company built a cognitive memory agent to provide agentic personalization for its hiring assistant, moving off GraphRAG in favor of a tree…
Thijs Simonian, a Stanford student and robotics worker at OpenAI, released a browser game on August 24th that uses Apple Maps data to create a playable San Francisco, allowing players to climb buildin…
Pew Research Center's Data Labs team analyzed nearly half a million webpages and found signs of AI authorship or editing on about 10% of them, with the share rising to 35% for pages published after Ch…
A National Bureau of Economic Research working paper analyzing 29.4 million U.S. LinkedIn profiles finds that 19.7% of established users retroactively edited a past job title or description between 20…
A Stanford study found that debate-based multi-agent architectures outperform other team strategies in complex reasoning tasks, but single agents often match or exceed their performance when given equ…
An observational study of 179 peer-to-peer messages between Claude Code sessions over five days found that cross-session messages always arrive at turn boundaries, never interrupting an active tool lo…
Latent Space reports that the AI industry is increasingly replacing human-made components of the machine intelligence pipeline with model-made ones, a trend it calls 'human simulation' that is 10% wor…
A developer who writes commercial copy for a living has shipped Cencurity, an open-source security gateway that proxies traffic between AI coding agents and LLM providers to mask sensitive data and in…
Veracode's Spring GenAI Code Security Update found that 45% of code generated by 150 large language models across 80 tasks contained known vulnerabilities, with security pass rates stuck at about 55% …
A Stanford research team (Saad-Falson et al., 2026) benchmarked small language models (SLMs) running on local hardware against cloud-based frontier LLMs, finding that SLMs can handle over 80% of real-…
Micron Technology announced on August 20 the launch of Micron Research Labs, a $10 billion, decade-long initiative to create the first dedicated AI memory research institution in the U.S., with a flag…
Fei-Fei Li, Stanford professor and cofounder of World Labs, said in a Bloomberg interview released Wednesday that she runs her AI startup like a 'tiger mom,' setting high standards for her young team.…
Virginia, which spent twenty years courting data centers with tax breaks and fast-tracked zoning, became the first U.S. state to tax the electricity those centers use, a reversal that Techstrong's spe…
Anthropic has published early evidence of Claude operating in live life sciences research workflows, with deployments at Stanford and MIT labs using the model for data-heavy analysis, experimental des…