Historical milestone · 1985
Therac-25 accidents
Reviewed through September 18, 2026
1985 · Historical milestone
Therac-25 accidents
- Era
- 1980s
- Theme
- Safety, security & alignment
- Evidence form
- Showed that catastrophic failures emerge from system interactions, not a single bad component, and that software safety requires process and organizational controls.
- School / paradigm
- Case investigation of radiation overdoses between 1985 and 1987 involving software races, interface design, organizational failures, and weak incident reporting
- Institution / context
- Safety-critical software community
- Researchers
- Nancy Leveson; Clark Turner; operators, regulators,; investigators
Researcher index
Nancy Leveson
Software and system safety · MIT
Therac-25 analysis and system safety engineering
Why it still matters. Shifted safety analysis from component bugs to sociotechnical system interactions.
Representative source for this researcher — not necessarily the source of this milestone: https://doi.org/10.1109/MC.1993.274940 (opens in a new tab)
School of thought
Safety, security, and machine ethics
Matched on representative researcher.
Intelligent systems must be treated as potentially fallible or adversarial components embedded in technical and social control structures.
Critique. Hard guarantees rarely cover adaptive learned systems and open environments; governance can lag capability.
Modern descendants. Alignment, prompt-injection defense, agent permissions, red teaming, incident response, and AI assurance.
Understand
Plain-language record, transferred from the reviewed source module.
Theory or experimental setup. Retrospective cases reveal failure mechanisms but do not by themselves produce complete predictive assurance.
Result / historical claim. Agent incident analysis, defense in depth, human factors, audit trails, and sociotechnical safety cases.
Apply
Professional implication, only where the reviewed record states one.
The checked-in record does not state a separate professional application for this entry. The topic page places it in the wider research lineage: Safety, security, and alignment.
Verify
Evidence status, stated limitations, and the external sources this record actually carries.
Evidence form. Showed that catastrophic failures emerge from system interactions, not a single bad component, and that software safety requires process and organizational controls.
Limitation / debate. https://doi.org/10.1109/MC.1993.274940
Source status. The source link below is the verified link our reviewed topic research already carries for this milestone.
Reproduce
A reproduction tutorial is linked only when one exists for this exact record.
A reproduction tutorial is not yet available for this entry. The closest reviewed material is Safety, security, and alignment.
Cite or share
APA-like: This historical record carries a year only, and no author or publisher of record in the checked-in data. An APA reference would have to invent that metadata.
BibTeX: BibTeX requires an author and publication venue. Historical lineage entries store a narrative record and its source link, not structured authorship, so the field would be fabricated.
Related
Appears in AI governance becomes measurable infrastructure.