Explore tools, prompts, skills, news and resources related to MIT.
Latest articles, prompts, use cases and editorial content about MIT
Factory has released Droid 1.0, a model-independent coding agent harness that enables programmatic tool calling by default. Its Script tool runs JavaScript in a sandbox, coordinating multiple tool calls while returning o...
Vercel Labs has released agent-desktop, an Apache-2.0-licensed CLI and C library that lets AI agents operate apps on macOS, Windows and Linux through operating-system accessibility trees rather than screenshots. The tool...
A biotech startup reportedly used an AI agent to choose a gene therapy and successfully inject the treatment into a live mouse’s brain. The supplied excerpt does not explain the experimental setup, human oversight or the...
Google DeepMind and the World Resources Institute have released ForTy, a global map using satellite data and AI to classify forests and other land into six categories, including primary forests, plantations and tree crop...
Claude has reportedly removed its five-hour usage limit, with the first Ultra users gaining access after being unlocked. The report specifically says that $200 Ultra subscribers are the first to use the change.Why it mat...
Google Chief Business Officer Philipp Schindler said strong growth in AI Mode queries had an impact because those queries monetized at a lower level. The disclosure highlights a business-model challenge as Google expands...
OpenAI is now seeking about $20 billion at a $1.25 trillion valuation, according to the Financial Times. The reported $10 billion reduction in its funding target signals a pullback in fundraising ambitions amid mounting...
OpenAI has reduced its latest fundraising target by $10 billion, according to a Financial Times report cited by The Information. The company initially sought $30 billion at a $1.4 trillion valuation and reportedly lowere...
AWS outlines a five-stage operating model for managing Amazon Bedrock generative AI costs: attribute spend to IAM principals, log requests with metadata, enforce budgets, optimize platform defaults, and run a review cade...
AWS introduced session endpoints for Amazon Bedrock AgentCore runtime, giving each agent session an authenticated URL that forwards HTTP/1.1, HTTP/2 and WebSocket traffic to ports the developer explicitly allows. The pos...
Dartmouth College provost Santiago Schnell resigned after an advisory committee found he failed to disclose significant AI use in an academic paper and a Washington Post op-ed, despite publisher disclosure requirements....
Microsoft Research and UC Berkeley researchers released TokenEconomizer, an Apache 2.0 open-source cost controller that plugs into Claude Code, Codex, GitHub Copilot CLI and Pi without modifying model weights or agent co...
VeriCUA is a platform-agnostic framework that treats task-completion verification for computer-using agents as dynamic evidence gathering and assessment. It first inspects available context to build a task rubric, then s...
Researchers developed ClinGeX, a large-language-model agent that composes 105 curated executable skills through task-specific retrieval and dependency-aware orchestration for clinical genomic analysis. On 223 temporally...
AWS published a walkthrough for configuring the ChatGPT desktop app and Codex to use OpenAI models through Amazon Bedrock in AWS GovCloud (US-West). The setup routes inference through the Bedrock Mantle endpoint in us-go...
MarkTechPost compares the source-code vulnerability agents shipped by Anthropic (Claude Security plugin for Claude Code), OpenAI (Codex Security CLI/SDK), Cloudflare (MIT-licensed Security Audit Skill) and Google (Mantis...
A new arXiv paper argues that existing benchmarks for predicting how many tokens an LLM will decode from prefill-phase hidden states conflate predictor quality with task difficulty, causing reported accuracy to collapse...
Researchers propose a scalable template-based augmentation pipeline that extracts safe templates from harmful prompts, translates them, and fills slots with culturally authentic harmful and benign entities. The work rele...
Researchers introduce MetaRefine, a lightweight architecture that refines existing image assessment scores using original-image geometry, multi-level visual features, and the frozen model's score. Across 100 configu...
FIRME is a registry-anchored memory graph designed to reconcile recurring investor observations into persistent canonical relationships while retaining source, time, and context. It uses rule-based within-period fusion t...
