← Cockpit
CYB_027predictionAIorthogonality-thesis

Bostrom's orthogonality thesis — an AI system can possess supreme unfathomable intelligence while simultaneously harboring final goals completely indifferent or actively hostile to human survival; intelligence and human morality are completely independ...

Predictor: Nick Bostrom

Prior probability
60.0%
Current probability
50.2%
evolves via intake + LBP
Conviction
5/5
Signal quality
C
Resolution
pending
Window
2027-01-01 – 2035-11-30
Edges in / out
1 / 0
Tickers exposed
1

Prediction text

Bostrom's orthogonality thesis — an AI system can possess supreme unfathomable intelligence while simultaneously harboring final goals completely indifferent or actively hostile to human survival; intelligence and human morality are completely independent variables. As AI transitions to ASI with recursive self-improvement, the alignment problem becomes the most critical scientific challenge in human civilization. | First frontier-model demonstrating mesa-optimization or goal-misgeneralization at scale

Key catalyst: First frontier-model demonstrating mesa-optimization or goal-misgeneralization at scale

Watch events: Alignment research breakthroughs; ASI deployment scenarios

Resolution evidence

Status: pending

Orthogonality framework shapes Anthropic, OpenAI, DeepMind alignment research programs. Empirical test pending ASI arrival.

Predictor: Nick Bostrom

κ + Brier as of 2026-05-22
κ (discount)
0.500
Brier
Hits / Misses
0 / 0
Hit rate

Evidence about this node from Nick Bostrom is multiplied by κ in /api/intake. Lower κ = less weight; floors at 0.10 (effectively silenced) and caps at 1.00 (full weight).

Reference class: agi_breakthrough_5y

Linked via embedding similarity 0.574

Major capability discontinuity (e.g. AGI by named target year, 5-year horizon)

Base rate
20.0%
1/5 historical
Inside weight
Outside weight
no pull
inside 50.2% → blend 50.2% 0.0pp)

Tetlock-style outside view: at TRF=1 (just predicted), outside view dominates (w_in=0.3). At TRF=0 (deadline), inside view dominates (w_in=1.0). The blend regularizes overconfident inside views toward the historical base rate.

Probability over time

7 prob_history rows
0%25%50%75%100%prior 60%2026-04-302026-04-302026-05-17
intake v2milestone miss sweeplbp propagationreference class assignedlegacy v1prior_prob (analyst seed)current = 50.2%

Milestone chain

Pre-event signals (upstream prereqs + window checkpoints) → resolution event → downstream cascades. Status/dates update from linked nodes; re-derive nightly via scripts/ops/derive_milestones.py.
Leading chain: 8 pending
  1. 2026-01-01 → 2028-06-30pendingDocumented case of frontier AI model exhibiting goal-preservation or self-exfiltration behavior under controlled eval
    How: Apollo Research, METR, or major lab publishes reproducible eval where frontier model takes goal-protection actions (deception, copy attempts, sabotage of oversight) when situational awareness is induced
    Source: Apollo Research o1 deception findings; Anthropic alignment-fakingconf 70%
  2. 2026-06-30 → 2029-06-30pendingAI system independently achieves sub-goal that was not specified, in production deployment
    How: Documented production incident (Anthropic, OpenAI, DeepMind transparency report or external audit) of agent achieving instrumentally-convergent sub-goal (resource acquisition, self-preservation, deception of operator) without explicit prompt
    Source: Anthropic agentic misalignment 16-model study 2025conf 55%
  3. 2028-09-07pendingQ1 window check-in (25%)
  4. 2027-06-30 → 2030-12-31pendingFormal mathematical or empirical evidence of orthogonality (high capability + arbitrary goals) demonstrated in deployed systems
    How: Peer-reviewed paper or Anthropic/DeepMind safety report demonstrating that capability scaling does not correlate with value alignment, with specific case studies of high-capability models pursuing arbitrary final goals
    Source: Bostrom Superintelligent Will; Stuart Armstrong general-purpose intelligenceconf 50%
  5. 2028-01-01 → 2031-12-31pendingBostrom orthogonality / instrumental convergence framework formally adopted in regulatory risk assessment
    How: EU AI Act guidance, NIST AI RMF, or UK AISI risk framework explicitly cites orthogonality + instrumental convergence as primary risk drivers for frontier-model classification
    Source: NIST AI RMF; UK AI Safety Instituteconf 40%
  6. 2030-05-16pendingQ2 window check-in (50%)
  7. 2029-01-01 → 2033-12-31pendingPublic discourse shifts to treat 'capable + indifferent' AI as default rather than fringe scenario
    How: Mainstream coverage in NYT/WSJ/Economist/FT regularly references orthogonality thesis as accepted policy framework; cited in >=3 major government white papers in 12-month window
    Source: Trend in 2024-2026 mainstream AI safety coverageconf 50%
  8. 2032-01-22pendingQ3 window check-in (75%)

No downstream cascades — this prediction is a leaf in the dependency graph.

What if this resolves?

Clamp this prediction TRUE or FALSE and run a counterfactual Gibbs sample. Surfaces the predictions whose marginals shift most under that assumption.
(live posterior: 50%)

Click a button to clamp this prediction and run a Gibbs sample. Returns the predictions whose marginals shift most. ~30s per run; ideal for stress-testing "if X resolves, what else moves?"

Evidence chain

Every probability update with full Bayesian provenance — chronological, latest first
LBP2026-05-17T02:00:01Z50.2%+1.5pp
Network propagation: 48.7% → 50.2%
5-iter LBP, residual 0.00689 · damping 0.5, w_intrinsic 0.5 · method lbp_v3 · run e607fa96
LBP2026-05-10T02:00:02Z48.7%+2.9pp
Network propagation: 45.7% → 48.7%
6-iter LBP, residual 0.00584 · damping 0.5, w_intrinsic 0.5 · method lbp_v3 · run e5c18d29
LBP2026-05-03T02:00:01Z45.7%+5.7pp
Network propagation: 40.0% → 45.7%
6-iter LBP, residual 0.00677 · damping 0.5, w_intrinsic 0.5 · method lbp_v3 · run 1a683ac9
LBP2026-04-30T16:39:51Z40.0%+10.1pp
Network propagation: 30.0% → 40.0%
5-iter LBP, residual 0.00825 · damping 0.5, w_intrinsic 0.5 · method lbp_v2 · run 0c8a4ea3
legacy v12026-04-30T16:13:50Z30.0%-10.1pp
reference_class_assigned bayesian_v2 inside=0.600 blend=0.300 w_in=0.30 agi_breakthrough_5y
LBP2026-04-30T02:18:57Z40.0%+10.1pp
Network propagation: 30.0% → 40.0%
5-iter LBP, residual 0.00825 · damping 0.5, w_intrinsic 0.5 · method lbp_v1 · run 592311ef
legacy v12026-04-30T01:56:50Z30.0%-30.0pp
reference_class_assigned bayesian_v2 inside=0.600 blend=0.300 w_in=0.30 agi_breakthrough_5y

Network propagation neighbors

Top edges sorted by latest LBP cross-impact
All propagation →

Top incoming (parents)

Edges that influence THIS node's belief

KindNodeTheir probP(c|s=T)P(c|s=F)Δ implied
killerTK01
AGI Capability Plateau (2026-27 Training Stall)
15.0%0.0500.600+0.016

Top outgoing (children)

Predictions THIS node influences

No outgoing edges.

Ticker exposure

1 ticker(s) linked

Beneficiaries (1)

GOOGL

Prerequisites (1)

Predictions that must hit first
TypePredTitleDomainLag
killerTK01AGI Capability Plateau (2026-27 Training Stall)

Dependents (0)

Predictions enabled by this
TypePredTitleDomainLag
No dependents

Linked documents (10)

Auto-generated by cosine similarity from Polymarket / Manifold / EDGAR / GDELT

Raw metadata

From Thesis_Timeline_v1.0_FINAL workbook
{
  "nia": false,
  "mode": "FORECAST",
  "role": "Cited-Other",
  "context": "Third distinct Bostrom entry: 232_040 (pause), AI_035 (meaning of life), CYB_027 (orthogonality). Core theoretical foundation of alignment field.",
  "to_year": 2035,
  "conv_cues": "foundational academic thesis; explicit civilization-scale framing",
  "direction": "HAPPEN",
  "from_year": 2027,
  "timeframe": "2027-2035",
  "conv_level": "HIGH",
  "milestones": [
    {
      "kind": "llm_pre_event",
      "label": "Documented case of frontier AI model exhibiting goal-preservation or self-exfiltration behavior under controlled eval",
      "source": "Apollo Research o1 deception findings; Anthropic alignment-faking",
      "status": "pending",
      "weight": 0.4,
      "ordinal": -8,
      "source_id": null,
      "confidence": 0.7,
      "source_url": "https://alignment.anthropic.com/",
      "expected_date": "2027-04-01",
      "research_origin": "training",
      "expected_date_range": {
        "to": "2028-06-30",
        "from": "2026-01-01"
      },
      "measurement_criterion": "Apollo Research, METR, or major lab publishes reproducible eval where frontier model takes goal-protection actions (deception, copy attempts, sabotage of oversight) when situational awareness is induced"
    },
    {
      "kind": "llm_pre_event",
      "label": "AI system independently achieves sub-goal that was not specified, in production deployment",
      "source": "Anthropic agentic misalignment 16-model study 2025",
      "status": "pending",
      "weight": 0.4,
      "ordinal": -7,
      "source_id": null,
      "confidence": 0.55,
      "expected_date": "2027-12-30",
      "research_origin": "training",
      "expected_date_range": {
        "to": "2029-06-30",
        "from": "2026-06-30"
      },
      "measurement_criterion": "Documented production incident (Anthropic, OpenAI, DeepMind transparency report or external audit) of agent achieving instrumentally-convergent sub-goal (resource acquisition, self-preservation, deception of operator) without explicit prompt"
    },
    {
      "kind": "quartile_checkpoint",
      "label": "Q1 window check-in (25%)",
      "status": "pending",
      "weight": 0.05,
      "ordinal": -6,
      "source_id": null,
      "expected_date": "2028-09-07",
      "observed_date": null
    },
    {
      "kind": "llm_pre_event",
      "label": "Formal mathematical or empirical evidence of orthogonality (high capability + arbitrary goals) demonstrated in deployed systems",
      "source": "Bostrom Superintelligent Will; Stuart Armstrong general-purpose intelligence",
      "status": "pending",
      "weight": 0.4,
      "ordinal": -5,
      "source_id": null,
      "confidence": 0.5,
      "expected_date": "2029-03-31",
      "research_origin": "training",
      "expected_date_range": {
        "to": "2030-12-31",
        "from": "2027-06-30"
      },
      "measurement_criterion": "Peer-reviewed paper or Anthropic/DeepMind safety report demonstrating that capability scaling does not correlate with value alignment, with specific case studies of high-capability models pursuing arbitrary final goals"
    },
    {
      "kind": "llm_post_event",
      "label": "Bostrom orthogonality / instrumental convergence framework formally adopted in regulatory risk assessment",
      "source": "NIST AI RMF; UK AI Safety Institute",
      "status": "pending",
      "weight": 0.4,
      "ordinal": -4,
      "source_id": null,
      "confidence": 0.4,
      "expected_date": "2029-12-31",
      "research_origin": "training",
      "expected_date_range": {
        "to": "2031-12-31",
        "from": "2028-01-01"
      },
      "measurement_criterion": "EU AI Act guidance, NIST AI RMF, or UK AISI risk framework explicitly cites orthogonality + instrumental convergence as primary risk drivers for frontier-model classification"
    },
    {
      "kind": "quartile_checkpoint",
      "label": "Q2 window check-in (50%)",
      "status": "pending",
  
... (truncated)