The research loop — and where AI is strong or weak
Literaturestrong recall · fake refs
→
Hypothesisnovel · often infeasible
→
Designgood protocols · lacks tacit knowledge
→
Execute in silicostrong engineering
→
Execute physicallyslow, costly, narrow
→
Analysefast · over-claims
→
Writefluent · sloppy
→
Verifythe bottleneck
Where AI is now strong: breadth, speed and engineering, and anywhere a cheap automatic checker exists (unit tests, Lean, benchmarks).
Where AI is still weak: research taste, backtracking, physical experiments, and honest uncertainty. Verification is the binding constraint.
The AI Scientist: the full loop, automated
Idea+ automatic novelty check
→
Experimentagent writes and runs code
→
Write-upLaTeX paper
→
AI reviewerscores the paper
~$15per generated paper (v1, 2024)
1 of 3AI-written papers passed peer review at an ICLR 2025 workshop
base modelpaper quality scales with the underlying LLM (Nature, 2026)
Workshops accept ~70%, humans picked what to submit, and the papers had citation errors. Passing review shows a reviewer was convinced, not that the result is true.
Automate the whole loop, from hypothesis to robot experiment to analysis.
Periodic Labs superconductors · semiconductors
The lab is a data engine: its experiments train frontier models.
Radical AI materials
Materials foundation models drive a self-driving lab.
Project Prometheus engineering · manufacturing
AI that learns from physical trial and error.
Core problem: LLMs are commoditised, so the moat is proprietary experimental data and verification by real experiment. Little public evidence of discoveries yet.
Who chose the problem, and who validated the result? Were the validators independent of the developers?
Is it new? Was a literature search done, and was it a rediscovery? (Erdős, A-Lab)
What was the oracle? Lean, wet lab, simulator or LLM judge, and could it be gamed?
How many attempts were made, and how were the shown ones selected? Look for best-of-n disclosure.
Is it auditable? Code, seeds, traces, prompts.
Does it generalise? Scale, a second dataset, a held-out test.
Systems that pass most of these checks: Erdős #728 (Lean), AlphaEvolve on 67 problems (successes and failures reported), Co-Scientist cf-PICI (an independent prior experimental result).
Trend lines (METR, compute, task difficulty), signs of self-improvement, and the evidence that keeps us humble.
How METR measures a "time horizon"
Task suite228 software / ML / cyber tasks (TH 1.1)
→
Human baselinesexperts timed on each task
→
Agent runsrepeated runs, auto-scored
→
Logistic fitP(success) vs log(human time)
50% horizon = the human task length at which the model succeeds half the time. The 80% horizon is much shorter, e.g. ~17 h vs ~3 h for the best 2026 model.
The METR time horizon: agents work for longer and longer
Approximate values from METR publications (v1.0/1.1 task suites: software, ML and cyber tasks). METR warns that horizons above ~16 h are unreliable as the suite saturates, and that analysis choices shift results by up to 20%. Doubling time ≈ 4–7 months.
Progress in numbers (2/2): inputs, speed and efficiency
×5 / yr
frontier training compute since 2020 (doubling ≈ 5 months), Epoch AI
×7–17 / yr
METR 50% horizon growth (doubling 131 days since 2023, 89 days since 2024)
5 min → ~17 h
METR 50% horizon, GPT-4 (2023) → Claude Mythos Preview (2026): ≈ 200×
~$6–10M
for one claimed math result: 10k agents × 88 h (forced Navier–Stokes, Sep 2026), at public API prices
~$15
per generated paper, AI Scientist v1 (2024)
$12 · $66
per reproduction attempt · per confirmed reproduction, RECLAIM (2026)
+40% / yr
energy efficiency (FLOP/s per watt) of leading ML chips, Epoch AI
÷33 in 1 yr
energy per median Gemini prompt, model + software + hardware (Google, Aug 2025)
÷9–900 / yr
price to reach a fixed capability level, depending on the task, Epoch AI
Capability grows faster than compute, and capability per watt grows faster than chips: algorithms, post-training (RL) and scaffolds add on top of hardware.
RECLAIM (2026): 100 NeurIPS-2025 papers; target number, tolerance and GPU budget fixed in advance; graded from logs by a separate model. The 3 variants = what the authors released.
128 vs 73reproductions claimed by agents vs confirmed by audit
~70%of the compute budget left unused when an attempt fails
#1 errorimplementing without checking against the paper's numbers
The missing skill is not engineering but scientific self-checking.
↺ cheap exact feedback → RL and search optimise against it directly
The general principle: AI progress scales with the speed and fidelity of the field's verifier
Mathexact proof checker
ML / CVnoisy metrics
Chemistry, materialsapproximate simulators
Biology, medicineslow wet labs, trials
fast, exact verifierslow, noisy verifier →
Three scenarios for 2030
Co-pilot plateau
AI is everywhere at L2–L3. Big speed-ups on coding and analysis, but verification capacity caps the end-to-end gain.
Verifiable-domain takeoff
Math, ML and the simulable parts of chemistry and materials see AI-led discovery. Biology and medicine stay human-validated.
Science factories
A few private labs with robots and models produce a large share of discoveries. That raises questions of access, publication and governance.
The deciding variable in each scenario is the cost of verification: formal tools, simulators, robotic labs and institutions.
Take-home messages
AI (co-)scientists are real but uneven. They are strong at engineering, breadth and speed, and weak at research taste and verification.
Progress follows verifiability: math leads, then ML, then simulable sciences, then wet-lab and clinical fields.
Co-scientist beats autonomous scientist today. Outside math, every validated discovery had humans owning the validation. In math, Lean can own it (Erdős #728), but humans still pick the problems and check the formal statements.
Judge claims by independent verification, not by peer-review acceptance or self-reported accuracy.
Capital is betting on data and labs, not models. Watch for the verification infrastructure.
Part 3
Where I am — and where I want to go?
What changed in my daily research, a bet for computer vision, and two research directions.