Matthew Gray
TGT Manager, Machine Intelligence Research Institute
Matthew Gray is TGT Manager at the Machine Intelligence Research Institute (MIRI). He previously worked as a data scientist at Indeed and Samsung, and in 2017 wrote MIRI's published response to Maciej Cegłowski's talk skeptical of superintelligence risk, arguing that long-term AI hazards are harder and more complex than short-term ones.
Key arguments & positions
- Argues long-term AI hazards are harder and more complex than short-term ones, and that attention to long-term risk helps draw attention to near-term misuse rather than distracting from it.
Accomplishments
- TGT Manager at the Machine Intelligence Research Institute (MIRI).
- Previously a data scientist at Indeed and Samsung.
Papers & key writings
Links
In the library
Nothing of theirs is filed in the hub yet. Browse the full library.
Recommended next
Hand-picked from the hub based on what Matthew Gray covers.
How Much Should We Spend to Reduce A.I.'s Existential Risk?
Stanford economist Charles I. Jones works out, in plain economic terms, how much money it would be worth spending to lower catastrophic risks from advanced AI — comparing it to the roughly 4 percent of GDP the U.S. effectively spent during Covid-19.
Why this: Covers AI and AI safety too
Squiggle Maximizer (formerly "Paperclip Maximizer")
LessWrong wiki article explaining the canonical AI safety thought experiment: how an artificial general intelligence with an innocuous goal could pose an existential risk by pursuing it single-mindedly. Covers the orthogonality thesis and instrumental convergence.
Why this: Covers AI and AI safety too
Anthropic releases new Mythos and Fable models amid RSI concerns
TechCrunch reports on Anthropic's Fable 5.2 and Mythos 5.2 release, pricing and system-card concerns about evaluating covert behavior. This is freely readable reporting; model capabilities are attributed to Anthropic and the system card, not independently established by the article.
Why this: Covers AI and AI safety too
Control Room: A central system to track and stop model workloads across our research infrastructure
OpenAI describes Control Room, an internal system for tracking and stopping model workloads across its research infrastructure. The company reports intervention performance and safety design; the article is free to read, but Control Room is not offered as a public tool.
Why this: Covers AI and AI safety too