{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2025-05-27-intology-zochi-acl-2025/","md":"https://postcutoff.com/e/2025-05-27-intology-zochi-acl-2025/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2025-05-27-intology-zochi-acl-2025","date":"2025-05-27","date_precision":"month","short_title":"Intology's 'Zochi' AI system gets a paper into the ACL 2025 main conference","deck":null,"takeaway":null,"category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":[{"n":1,"title":"Intology: Zochi's paper accepted to ACL 2025","url":"https://www.intology.ai/blog/zochi-acl","type":"official","group":"primary","domain":"intology.ai"},{"n":2,"title":"ACL 2025 main conference papers","url":"https://2025.aclweb.org/program/main_papers/","type":"docs","group":"primary","domain":"2025.aclweb.org"},{"n":3,"title":"LessWrong discussion: Zochi publishes a paper","url":"https://www.lesswrong.com/posts/LtsgfGsXpiLTSGpaW/zochi-publishes-a-paper","type":"discussion","group":"reactions","domain":"lesswrong.com"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Intology"],"title":"Intology's 'Zochi' AI system gets a paper into the ACL 2025 main conference","summary":"In May 2025 Intology said its autonomous research agent Zochi produced 'Tempest', a paper on multi-turn LLM jailbreaking via tree search, that was accepted to the main conference of ACL 2025 (acceptance rate ~20%) — claimed as the first AI-generated paper to pass peer review at an A* main venue.","key_facts":["Paper: 'Tempest: Automatic Multi-Turn Jailbreaking of LLMs with Tree Search'","Meta-review score 4/5; Intology claims it ranked in the top 8.2% of submissions","Human role per Intology: manuscript preparation only (figures, citation formatting, minor fixes)","Autonomy claims are self-reported; exact announcement day not verified (month precision)"],"key_numbers":[],"tags":["ai-scientist","autonomous-research","peer-review","nlp"],"science":{"field":"computer-science","subfield":"NLP / AI safety","problem":"Automated research reaching a top-tier main conference","result":"An AI-generated paper on automated multi-turn jailbreaking was accepted to the ACL 2025 main conference.","open_since":"","ai_system":["Zochi"],"human_role":"AI-assisted: agent claimed to handle ideation, experiments and writing; humans formatted the manuscript","verification":{"key":"none","label":"Unverified claim","text":"Peer review at ACL 2025 (acceptance confirmed); autonomy self-reported"},"status":"confirmed","shock":""},"body_md":"## What happened\n\nIntology's agent Zochi generated a method (Tempest) for automatically jailbreaking language models over multiple conversation turns using tree search, ran the experiments and drafted the paper, which passed ACL 2025 main-track peer review.\n\n## Why it matters\n\nIt moved AI-authored research from workshop level (Sakana, March 2025) to a selective main track within months, though the degree of autonomy could not be independently audited.","disputed":[],"related":[{"id":"2025-03-12-sakana-ai-scientist-v2-peer-review","url":"https://postcutoff.com/e/2025-03-12-sakana-ai-scientist-v2-peer-review/","date":"2025-03-12","date_precision":"day","short_title":"Sakana's AI Scientist-v2 writes the first fully AI-generated paper to pass peer review","deck":null,"takeaway":"It was the first demonstration that a fully automated pipeline could clear human peer review, even at a workshop with a higher acceptance rate than main tracks.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":4,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Sakana AI","University of British Columbia","University of Oxford"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":null}