{
  "schema_version": "1.2.0",
  "rubric_version": "1.1",
  "license": "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)",
  "record": {
    "id": "O-0202",
    "slug": "machine-intelligence-research-institute",
    "title": "Machine Intelligence Research Institute",
    "aliases": [
      "MIRI"
    ],
    "status": "published",
    "last_reviewed": "2026-09-25",
    "review_interval_days": 90,
    "steward": null,
    "provenance": {
      "drafted_by": "ai",
      "reviewed_by": [
        "codex-review"
      ]
    },
    "risk_flags": [],
    "flags": [],
    "kind": "research-org",
    "homepage": "https://intelligence.org/",
    "one_liner": "A nonprofit focused on preventing human extinction from artificial superintelligence; its Technical Governance Team publishes designs and analyses for verifying AI agreements.",
    "sources": [
      {
        "source": "S-3609",
        "supports": "nonprofit focus on preventing human extinction from artificial superintelligence"
      },
      {
        "source": "S-0018",
        "supports": "low-trust compute verification system overview"
      },
      {
        "source": "S-0038",
        "supports": "side-channel suppression with retrofitted defences"
      },
      {
        "source": "S-0014",
        "supports": "analysis of TEEs for privacy-preserving monitoring (Technical Governance Fellowship)"
      },
      {
        "source": "S-0005",
        "supports": "survey of mechanisms to verify international agreements; interconnect bandwidth limits"
      },
      {
        "source": "S-0063",
        "supports": "draft international agreement: monitored facilities and tracking of chip production"
      },
      {
        "source": "S-3380",
        "supports": "six TGT papers at the ICML 2026 TAIGR workshop; best-paper award for bit-exact inference verification"
      },
      {
        "source": "S-0020",
        "supports": "bit-exact inference verification paper"
      },
      {
        "source": "S-0037",
        "supports": "detecting hidden training from GPU telemetry"
      },
      {
        "source": "S-3220",
        "supports": "interconnect-limit monitoring prototype on two nodes with four A100 GPUs"
      }
    ],
    "type": "organization",
    "url": "https://trustbutveri.fyi/organizations/machine-intelligence-research-institute/",
    "source_file": "content/organizations/machine-intelligence-research-institute.md",
    "flags_all": [],
    "body_markdown": "MIRI describes itself as \"a nonprofit focused on preventing human extinction from artificial superintelligence\" [[S-3609]]. Its publications on verifying AI agreements, several of them from its Technical Governance Team, include:\n\n- **Low-trust verification system.** Cankaya's system overview combines network taps, sampled recomputation, memory challenges and facility monitoring in one reference architecture for near-term, low-trust compute verification [[S-0018]]. See [[I-0012]], [[M-0013]], [[M-0001]] and [[M-0016]].\n- **Side-channel suppression.** A post on suppressing side channels in an untrusted data centre with retrofitted defences sets out channel classes, attenuation targets and costs [[S-0038]]; see [[M-0022]].\n- **TEEs for monitoring.** A post written in MIRI's Technical Governance Fellowship analyses trusted execution environments for privacy-preserving monitoring [[S-0014]]. It contrasts the usual confidential-computing adversary, a dishonest operator, with a state that has physical access to data centres [[S-0014]]. See [[M-0008]], [[M-0023]] and [[M-0025]].\n- **Mechanisms survey.** Scher and Thiergart survey mechanisms for verifying international agreements about AI development, with a detailed analysis of [[M-0014|interconnect bandwidth limits]] [[S-0005]].\n- **Draft agreement.** A draft international agreement would prohibit concentrations of more than 16 H100-equivalents outside monitored facilities and would track new chip production [[S-0063]]; see [[C-0001]].\n- **Workshop papers.** MIRI reports that six Technical Governance Team papers appeared at the ICML 2026 Workshop on Technical AI Governance Research [[S-3380]]. They include bit-exact inference verification, which won the workshop's best-paper award [[S-3380]] [[S-0020]], and detection of hidden training from GPU telemetry [[S-0037]]. See [[M-0002]] and [[M-0021]].\n- **Interconnect prototype.** A 2026 post reports a prototype, built under Scher's supervision, that monitors inter-node traffic against a threshold on a two-node cluster with four A100 GPUs [[S-3220]]. See [[M-0014]].",
    "body_text": "MIRI describes itself as \"a nonprofit focused on preventing human extinction from artificial superintelligence\" [S-3609]. Its publications on verifying AI agreements, several of them from its Technical Governance Team, include: - Low-trust verification system. Cankaya's system overview combines network taps, sampled recomputation, memory challenges and facility monitoring in one reference architecture for near-term, low-trust compute verification [S-0018]. See Low-trust AI compute verification system overview, Network taps and certifiers, Sampled inference recomputation and Timed challenge-response and memory-occupation challenges. - Side-channel suppression. A post on suppressing side channels in an untrusted data centre with retrofitted defences sets out channel classes, attenuation targets and costs [S-0038]; see Side-channel suppression for isolated facilities. - TEEs for monitoring. A post written in MIRI's Technical Governance Fellowship analyses trusted execution environments for privacy-preserving monitoring [S-0014]. It contrasts the usual confidential-computing adversary, a dishonest operator, with a state that has physical access to data centres [S-0014]. See TEE remote attestation for AI workloads, Safeguard attestation and Confidential multi-party verification. - Mechanisms survey. Scher and Thiergart survey mechanisms for verifying international agreements about AI development, with a detailed analysis of interconnect bandwidth limits [S-0005]. - Draft agreement. A draft international agreement would prohibit concentrations of more than 16 H100-equivalents outside monitored facilities and would track new chip production [S-0063]; see Compute stock is at most a declared amount. - Workshop papers. MIRI reports that six Technical Governance Team papers appeared at the ICML 2026 Workshop on Technical AI Governance Research [S-3380]. They include bit-exact inference verification, which won the workshop's best-paper award [S-3380] [S-0020], and detection of hidden training from GPU telemetry [S-0037]. See Deterministic and bit-exact inference and Workload classification from telemetry and side channels. - Interconnect prototype. A 2026 post reports a prototype, built under Scher's supervision, that monitors inter-node traffic against a threshold on a two-node cluster with four A100 GPUs [S-3220]. See Bandwidth limits and compartmentalization.",
    "referenced_by": [
      {
        "id": "M-0014",
        "title": "Bandwidth limits and compartmentalization",
        "url": "https://trustbutveri.fyi/mechanisms/bandwidth-limits-and-compartmentalization/"
      },
      {
        "id": "M-0025",
        "title": "Confidential multi-party verification",
        "url": "https://trustbutveri.fyi/mechanisms/confidential-multi-party-verification/"
      },
      {
        "id": "M-0015",
        "title": "Memory wiping and proofs of secure erasure",
        "url": "https://trustbutveri.fyi/mechanisms/memory-wiping-and-secure-erasure/"
      },
      {
        "id": "M-0012",
        "title": "Model identity attestation",
        "url": "https://trustbutveri.fyi/mechanisms/model-identity-attestation/"
      },
      {
        "id": "M-0013",
        "title": "Network taps and certifiers",
        "url": "https://trustbutveri.fyi/mechanisms/network-taps-and-certifiers/"
      },
      {
        "id": "M-0010",
        "title": "On-chip telemetry from timing, memory and performance counters",
        "url": "https://trustbutveri.fyi/mechanisms/on-chip-telemetry/"
      },
      {
        "id": "M-0007",
        "title": "Proofs of useful work for capacity accounting",
        "url": "https://trustbutveri.fyi/mechanisms/proofs-of-useful-work/"
      },
      {
        "id": "M-0023",
        "title": "Safeguard attestation",
        "url": "https://trustbutveri.fyi/mechanisms/safeguard-attestation/"
      },
      {
        "id": "M-0001",
        "title": "Sampled inference recomputation",
        "url": "https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/"
      },
      {
        "id": "M-0022",
        "title": "Side-channel suppression for isolated facilities",
        "url": "https://trustbutveri.fyi/mechanisms/side-channel-suppression/"
      },
      {
        "id": "M-0008",
        "title": "TEE remote attestation for AI workloads",
        "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/"
      },
      {
        "id": "M-0016",
        "title": "Timed challenge-response and memory-occupation challenges",
        "url": "https://trustbutveri.fyi/mechanisms/timed-challenge-response/"
      },
      {
        "id": "M-0021",
        "title": "Workload classification from telemetry and side channels",
        "url": "https://trustbutveri.fyi/mechanisms/workload-classification-from-telemetry/"
      },
      {
        "id": "I-0012",
        "title": "Low-trust AI compute verification system overview",
        "url": "https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/"
      },
      {
        "id": "S-0038",
        "title": "Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses",
        "url": "https://trustbutveri.fyi/sources/cankaya-suppressing-side-channels/"
      },
      {
        "id": "S-0018",
        "title": "A System Overview for Near-Term, Low-Trust AI Compute Verification",
        "url": "https://trustbutveri.fyi/sources/cankaya-system-overview-low-trust-compute-verification/"
      },
      {
        "id": "S-3609",
        "title": "About MIRI",
        "url": "https://trustbutveri.fyi/sources/miri-about/"
      },
      {
        "id": "S-3380",
        "title": "Summary: TGT's 2026 ICML Papers",
        "url": "https://trustbutveri.fyi/sources/miri-tgt-2026-icml-papers/"
      },
      {
        "id": "S-0063",
        "title": "An International Agreement to Prevent the Premature Creation of Artificial Superintelligence",
        "url": "https://trustbutveri.fyi/sources/scher-agreement-prevent-premature-asi/"
      },
      {
        "id": "S-3220",
        "title": "De-risking Interconnect Limits for AI Verification",
        "url": "https://trustbutveri.fyi/sources/scher-derisking-interconnect-limits/"
      },
      {
        "id": "S-0005",
        "title": "Mechanisms to Verify International Agreements About AI Development",
        "url": "https://trustbutveri.fyi/sources/scher-mechanisms-verify-ai-agreements/"
      },
      {
        "id": "S-0014",
        "title": "On TEEs for Privacy-Preserving Monitoring in AI Governance",
        "url": "https://trustbutveri.fyi/sources/zhao-tees-privacy-preserving-monitoring/"
      }
    ]
  }
}