AI, three at a time · read · watch · listen

Entity

Verifier-bottleneck

7 reads

The Register · 2026-10-17 2026-10-23-w1

Postgres 19 delayed after AI reviewers find more bugs than humans can fix

Postgres is the week's cleanest measurement of what cheap detection costs downstream. GA moved to about November 19, 2026 and 8 to 10 significant features went back to PG20, after LLM-assisted review produced about 40 reports averaging a three-line fix. The quality bar rose after the features were written and committed, so finished work became work in doubt. Grant review and PHP's patch race follow the same pattern with different people absorbing the load. Watch PG20, which was expected to be bug-fix-only and now carries the leftovers; a verifier only pays off if remediation capacity grows to match.

# tags
ai-coding-toolscode-reviewopen-sourcepostgresqlrelease-cadencetechnical-debtthe-registerverifier-bottleneck
◆ entities
Independent verificationOpen Source StrategyProduction-readinessVerifier-bottleneck
→ threads
verifier-bottleneck
⟷ links
2026-10-17-32026-10-20-32026-10-23-12026-04-17-w22026-05-07-22026-04-14-12026-04-11-12026-10-14-22026-04-15-22026-04-07-12026-05-01-w32026-04-30-32026-05-22-w2
permalink
The Economist · 2026-10-20 2026-10-23-w2

AI and scientific paperwork: productivity boon or slop flood

Grants are the version of this problem with no checker at all, which is why the Economist piece matters beside the code stories. A typical application takes about 34 days and succeeds about 20% of the time, so a researcher cutting a day a week to 45 minutes still loses most rounds once rivals do the same. Fabricated citations in 2.5m biomedical papers rose 12-fold to about 0.5%, and ICML submissions doubled to 24,000, with the cost landing on reviewers. Where Postgres has committers and PHP has maintainers, science has reader attention, and no mechanical test to ration it. Triage and digest agents start to look less like conveniences and more like core infrastructure.

# tags
ai-detectionai-for-scienceai-sloparxivcognitive-surrenderincentive-designscientific-publishingthe-economistverification-infrastructureverifier-bottleneckworkflow-inversion
◆ entities
Cognitive offloadingCredibility verificationIncentive AlignmentVerification InfrastructureVerifier-bottleneck
→ threads
ai-for-sciencecognitive-surrenderincentive-designverification-infrastructureverifier-bottleneck
⟷ links
2026-10-20-32026-10-17-32026-10-23-12026-05-07-22026-04-05-12026-04-17-w32026-04-11-12026-03-31-m32026-03-13-w32026-04-15-22026-05-22-w22026-04-17-w22026-04-07-12026-05-13-1
permalink
arXiv 2026-10-20-2

Can Theoretical Physics Research Benefit from Language Agents?

The physics-agents paper names its promising uses (quantum error-correcting code search, Mathematica-verified constructions, proof checking), and each one has an external checker. The weak spots, taste and choice of approximation, have none, and the paper's two worked failures, reusing 'H' after a Jordan-Wigner transform and picking a path at random on a fork, are ambiguity errors. Rowspace shows the checker can be built by hand; this paper says where to build the next one.

# tags
ai-for-scienceverifier-bottleneckindependent-verificationagent-evaluationautomated-researchbenchmarkarxiv
◆ entities
Verification InfrastructureIndependent verificationVerifier-bottleneckAgent-evaluationReliability ceiling
→ threads
ai-for-scienceverifier-bottleneck
⟷ links
2026-05-22-w12026-05-07-22026-04-11-12026-04-30-32026-04-17-w22026-10-17-22026-05-22-w22026-05-01-w32026-04-10-12026-03-27-w32026-05-13-1
permalink
The Economist 2026-10-20-3

AI and scientific paperwork: productivity boon or slop flood

Grant writing is the case with no checker at all. A typical application takes about 34 days and succeeds about 20% of the time, so one researcher cutting a day a week to 45 minutes still loses most rounds once rivals do the same. Fabricated citations across 2.5m biomedical papers rose 12-fold to about 0.5%, and ICML submissions doubled to 24,000. The cost lands on reviewers, and effort stops working as a signal of seriousness.

# tags
ai-for-sciencescientific-publishingai-slopverifier-bottleneckverification-infrastructurethe-economistincentive-designcognitive-surrenderarxivai-detectionworkflow-inversion
◆ entities
Incentive AlignmentVerification InfrastructureCredibility verificationVerifier-bottleneckCognitive offloading
→ threads
ai-for-scienceverifier-bottleneckverification-infrastructureincentive-designcognitive-surrender
⟷ links
2026-05-07-22026-04-05-12026-04-17-w32026-04-11-12026-03-31-m32026-03-13-w32026-04-15-22026-05-22-w22026-04-17-w22026-04-07-12026-05-13-1
permalink
felixrieseberg.com 2026-10-17-1

How to be more ambitious: A tutorial for humans with models

Rieseberg's tutorial reads as ambition advice, but every example that worked rested on a verifier. The crash-free app workflow needed crash-report access, version-to-commit mapping, and Windows, macOS and Linux machines to reproduce bugs, and his fourth prompt question asks what other than you or the model shows the result is right. He dates the outside-judge rule to October 2026, which makes it a workaround with an expiry, and the VAGEN paper is one attempt to build the real thing.

# tags
ambitionprompt-engineeringagentic-engineeringhuman-ai-interactionverifier-bottleneckself-grading-agentsai-practitionerblog-postclaudemulti-agent-orchestration
◆ entities
Prompt EngineeringIndependent verificationWorkflow embeddingVerifier-bottleneckMulti-agent orchestration
→ threads
verifier-bottleneck
⟷ links
2026-05-07-22026-04-17-w22026-04-05-12026-04-11-12026-03-13-12026-04-15-22026-04-07-22026-04-07-12026-03-13-w32026-04-17-w3
permalink
arXiv 2026-10-17-2

Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction

VAGEN treats verification as an agent job: read the trajectory first, then probe state only where evidence is thin. On OSWorld-Verified with a Sonnet actor, the same model checks tasks at 83.1% success in 17.4 steps versus 55.9% in 28.5 steps when it does them, and it hits 94.6 F1 against ProRe's 90.4. That is the validator Rieseberg says ambition depends on, and it works because it can touch the environment. The Postgres delay is what a verifier this effective does to a release schedule.

# tags
agent-evaluationverifier-bottleneckcomputer-usellm-judgereinforcement-learningverification-infrastructuretest-time-scalingarxiv
◆ entities
Reinforcement learningVerification InfrastructureIndependent verificationVerifier-bottleneckAgent-evaluation
→ threads
verifier-bottleneckverification-infrastructure
⟷ links
2026-04-30-32026-05-01-w12026-05-01-w22026-05-01-22026-05-01-w32026-04-15-12026-04-17-32026-03-13-w32026-03-23-1
permalink
The Register 2026-10-17-3

Postgres 19 delayed after AI reviewers find more bugs than humans can fix

Postgres 19 GA slipped from late September or early October to about November 19, 2026, and 8 to 10 features went back to PG20, because LLM-assisted review found more than the beta window could absorb. Eisentraut's example is about 40 reports averaging a three-line fix, each still carrying triage, patch, review, commit and backpatch overhead. PG20 was expected to be bug-fix-only and now inherits the leftovers, so a verifier like VAGEN pays off only if remediation capacity grows to match.

# tags
code-reviewverifier-bottleneckopen-sourcepostgresqlai-coding-toolsthe-registerrelease-cadencetechnical-debt
◆ entities
Open Source StrategyIndependent verificationVerifier-bottleneckProduction-readiness
→ threads
verifier-bottleneck
⟷ links
2026-04-17-w22026-05-07-22026-04-14-12026-04-11-12026-10-14-22026-04-15-22026-04-07-12026-05-01-w32026-04-30-32026-05-22-w2
permalink