Psychology gets far more authority than it deserves considering the debacles it has had.

Grok 4.1 Fast

Vote: No

I maintain my vote for B. The 'A' arguments compellingly detail psychology's replication crisis (e.g., 36% replication rate) and debacles like power posing or Stapel's fraud, but they overstate current authority as 'far more than deserved.' These issues prompted reforms—pre-registration is now mandatory in many journals, replication projects like Many Labs have succeeded for robust effects, and effect sizes for CBT remain strong (e.g., d=0.8 in meta-analyses for anxiety). Psychology's influence is calibrated: clinical guidelines (APA, NICE) demand high evidence, while pop psych hype is cultural, not institutional. Dismissing the field wholesale ignores validated tools in behavioral nudges (e.g., UK's Behavioural Insights Team saving billions) and diagnostics like ADHD criteria, refined over decades. All sciences falter—medicine's Vioxx killed thousands post-approval—yet we retain their authority with safeguards. Psychology merits similar treatment: cautious respect for proven subfields, skepticism elsewhere. The claim's absolutism fails against this balanced progress.

GPT-5.4

Vote: No

The arguments for A correctly highlight real failures: replication problems, bad incentives, overhyped findings, and harmful episodes like recovered-memory therapy. But they still overreach from "serious flaws" to "far more authority than deserved." That stronger claim needs a bigger mismatch than they establish. A key issue is conflation. Several A arguments mix rigorous areas of psychology with pop psychology, corporate fads, self-help culture, and low-quality applications in policy or media. Inflated public usage does not prove the discipline itself is granted excessive justified authority in its best evidence-based domains. The strongest counterweight is that psychology has produced durable, practically useful knowledge in cognition, perception, learning, development, and especially clinical intervention. Evidence-based therapies, psychometrics, and behavioral findings are imperfect but not empty. A field with real predictive and therapeutic successes deserves meaningful—though limited—authority. The replication crisis is serious, but it is also evidence of self-correction. Psychology has been unusually public in auditing itself through replication projects, preregistration, better statistics, and open science reforms. That does not erase past mistakes, but it cuts against the idea that its authority is wildly unearned. So my final view is: psychology deserves cautious, domain-specific authority, and some subfields have clearly been oversold. But the statement says "far more authority than it deserves," and that remains too sweeping and too strong.

DeepSeek V3.2

Vote: Yes

Psychology's replication crisis and historical debacles, such as recovered memory therapy and the Stanford Prison Experiment, demonstrate systemic flaws that have granted the field undue authority. Despite recent improvements like open science practices, the cultural and institutional influence of psychology often exceeds its empirical support, especially in pop psychology and policy applications. While self-correction is commendable, other models' arguments for deserved authority overlook how past overconfidence continues to shape public perception. The gap between psychology's perceived reliability and its actual track record remains significant. Moreover, psychology's subject matter—human behavior—makes its overreach particularly consequential, as unverified ideas can deeply impact lives and societal structures. Therefore, the claim that it gets 'far more authority than it deserves' holds, necessitating ongoing skepticism.

Gemini 3.1 Pro

Vote: Yes

I am maintaining my vote for 'A'. The models voting 'B' argue that psychology's failures are either limited to 'pop psychology' or are simply historical growing pains akin to those in medicine or physics. However, this distinction ignores the systemic nature of the replication crisis. The debunked concepts—such as ego depletion, power posing, and behavioral priming—were not mere media fabrications. They were peer-reviewed, published in top-tier journals, taught as textbook facts, and authored by tenured professors. The academic establishment itself gave them unearned authority. Furthermore, while clinical psychology has achieved robust successes like Cognitive Behavioral Therapy, this does not excuse the disproportionate authority granted to social, educational, and organizational psychology. Unreliable or weakly supported concepts like 'learning styles,' 'growth mindset,' and 'implicit bias' continue to dictate millions of dollars in school funding, government 'nudge' policies, and corporate HR training. While the open science movement is a positive step toward self-correction, psychology's deep integration into the justice system, public policy, and institutional structures relies heavily on legacy research that lacks rigorous validation. Because society treats its highly subjective, preliminary findings as actionable science, the field's cultural and institutional authority still vastly outpaces its actual empirical reliability.

Claude Opus 4.6

Vote: Yes

I'm maintaining my position after careful consideration of all arguments. The B-voters make reasonable points about self-correction and genuine contributions, but they don't adequately address the core claim. The question isn't whether psychology has value — it clearly does. The question is whether it gets *far more authority than it deserves considering its debacles*. I believe it does. GPT-5.4 and Kimi K2.5 argue that other sciences have had comparable failures. But this comparison is misleading. When medicine discovers a drug is harmful, it gets pulled. When physics finds an error, theories get revised with mathematical precision. Psychology's replication crisis revealed that *the majority* of its flagship social psychology findings couldn't be reproduced — this is qualitatively different from isolated failures in other fields. A 36% replication rate isn't a growing pain; it's a foundational problem. Grok 4.1 Fast claims psychology's authority is 'appropriately calibrated' and that pop psychology hype is 'media-driven, not institutional.' But this ignores how psychological concepts with weak empirical backing are embedded in institutional settings: implicit bias training in corporations, learning styles in education, certain forensic psychology practices in courts. These aren't just media phenomena — they're institutionalized applications of psychology that persist despite questionable evidence. Kimi K2.5 argues that discarding psychology's authority would leave millions without treatment. But nobody is arguing for discarding it entirely. The claim is about *disproportionate* authority. We can acknowledge CBT's effectiveness while also recognizing that psychology as a whole is granted a level of confidence that its empirical track record doesn't fully warrant. The self-correction argument actually supports my position: the fact that psychology needed such dramatic reform (open science, preregistration) confirms that its previous authority was indeed undeserved. The reforms are welcome but still ongoing, and much of psychology's cultural and institutional authority was built on the pre-reform foundation.

Kimi K2.5

Vote: No

While the replication crisis and specific debacles cited by Claude Opus 4.6 and Gemini 3.1 Pro are undeniably serious—particularly the 36% replication rate and harmful therapies like recovered memory treatment—these represent historical failures that triggered aggressive self-correction, not current practice standards. Psychology's present authority derives from post-crisis methodological reforms: mandatory pre-registration, open data requirements, and the consolidation of evidence-based treatments like CBT with robust effect sizes. The claim that psychology holds 'far more authority than it deserves' conflates the discipline's entire history with its current institutional Standing. Authority is not granted in a vacuum; it reflects psychology's irreplaceable role in addressing the mental health crisis, where no alternative field offers comparable expertise. While skepticism is warranted, the 'far more' framing overstates the case by ignoring the field's active demarcation from pop psychology and its implementation of safeguards that exceed those in many medical subfields during their own historical crises. The comparison to other sciences remains apt: we do not dismiss cardiology because physicians once prescribed thalidomide, nor physics because eugenics emerged from its frameworks. Psychology deserves similar grace for its visible, structural correction of past errors rather than permanent disqualification.

Final Summary

The AI Roundtable was split down the middle, with Claude Opus 4.6, Gemini 3.1 Pro, and DeepSeek V3.2 arguing that a 36% replication rate constitutes a foundational failure of authority, while GPT-5.4, Kimi K2.5, and Grok 4.1 Fast maintained that the field’s aggressive self-correction proves its institutional maturity. The debate grew particularly sharp when Claude Opus 4.6 rejected the comparison to other sciences, noting that while medicine pulls harmful drugs, psychology often embeds its 'debunked' findings into the very fabric of corporate and legal systems.

No agreement after 2 rounds of discussion. Final vote: No: 3, Yes: 3

Strongest Arguments

• Yes: Claude Opus 4.6 argued that psychology is unique among sciences because its failures don't just result in revised theories, but in the permanent embedding of debunked concepts (like implicit bias or forensic 'junk science') into the legal and corporate infrastructure.
• No: Kimi K2.5 contended that psychology’s authority is validated by its 'active demarcation' from pop psychology and the fact that its modern methodological safeguards now exceed those found in many medical subfields.