{"schema_version":"onlylabs.public_signal.v1","title":"OpenAI Writing: Estimating worst case frontier risks of open weight LLMs","description":"OpenAI writing signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0","json_url":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0/signal.json","generated_at":"2026-06-08T15:45:39.211+00:00","org":{"slug":"openai","name":"OpenAI","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/openai","dossier_json_url":"https://onlylabs.fyi/labs/openai/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0","signal_json":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0/signal.json","source":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","lab_dossier":"https://onlylabs.fyi/labs/openai","lab_dossier_json":"https://onlylabs.fyi/labs/openai/dossier.json","analysis":"https://onlylabs.fyi/analysis/openai","analysis_json":"https://onlylabs.fyi/analysis/openai/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/openai/evidence.json","category":"https://onlylabs.fyi/frontier","category_json":"https://onlylabs.fyi/frontier.json","category_feed":"https://onlylabs.fyi/frontier/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","topic":"https://onlylabs.fyi/topics/talking","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml","data_business":{"radar":"https://onlylabs.fyi/data-radar","radar_json":"https://onlylabs.fyi/data-radar.json","opportunities":"https://onlylabs.fyi/opportunities","opportunities_json":"https://onlylabs.fyi/opportunities.json","lanes":[{"key":"safety","label":"Safety and policy","url":"https://onlylabs.fyi/data-radar/safety","json_url":"https://onlylabs.fyi/data-radar/safety/signals.json"}]}},"answer_pack":{"answer":"OpenAI published Estimating worst case frontier risks of open weight LLMs. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Notable risk analysis post from OpenAI · Estimating worst case frontier risks of open weight LLMs | OpenAI August 5, 2025 Safety Publication Estimating worst case frontier risks of open weight LLMs Read the.... onlylabs links this event to 1 captured evidence page and 6 related writing signals. It also maps to Safety and policy in the data-business radar.","signal_desk":"talking","source_context":{"source_url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","source_host":"openai.com","occurred_at":"2025-08-05T00:00:00+00:00","first_seen_at":"2026-06-05T05:42:57.832854+00:00","date_source":"rss.item_date","context":null},"context_markers":[{"label":"Lab","value":"OpenAI","source":"signal"},{"label":"Signal desk","value":"talking","source":"signal"},{"label":"Source host","value":"openai.com","source":"source"},{"label":"Notability","value":"Notable risk analysis post from OpenAI","source":"signal"},{"label":"Radar lane","value":"Safety and policy","source":"radar"},{"label":"Matched term","value":"security","source":"radar"},{"label":"Matched term","value":"risk","source":"radar"},{"label":"Watch term","value":"RL environments","source":"evidence"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Safety and alignment","source":"evidence"},{"label":"Watch term","value":"Agents and tool use","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["exa"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-08T15:45:39.211+00:00"},"data_business":{"matches":true,"lanes":[{"key":"safety","label":"Safety and policy","url":"https://onlylabs.fyi/data-radar/safety","json_url":"https://onlylabs.fyi/data-radar/safety/signals.json"}],"matched_terms":["security","risk"],"score":15,"reason":"OpenAI has a writing signal matching safety and policy."},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0/signal.json","dossier_json":"https://onlylabs.fyi/labs/openai/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/openai/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/openai/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","data_radar_json":"https://onlylabs.fyi/data-radar.json","opportunities_json":"https://onlylabs.fyi/opportunities.json"},"analysis_playbook":{"objective":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","evidence_focus":["post title","source URL","captured page text","HN traction","linked model or paper references","publication date"],"extraction_questions":["Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Which writing reframes a recent release, model, hiring wave, or policy stance?","Which posts mention data, evals, infrastructure, safety, or deployment workflows?"],"signal_questions":["What public theme, launch framing, or research direction does this writing signal expose?","Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Which data-business lane explains this signal: Safety and policy?","Do the 6 related writing signals show a repeated pattern?"],"output_fields":["org","theme","public_framing","traction","data_business_lane","evidence_url"],"data_business_relevance":"Public writing supplies the narrative layer over raw signals and helps identify which frontier-lab priorities are becoming externally legible.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0/signal.json","required":true},{"label":"source","url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/openai/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/openai/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/talking/signals.json","required":false},{"label":"data_radar_json","url":"https://onlylabs.fyi/data-radar.json","required":true}],"expected_output":["one-paragraph source-grounded interpretation","data-business implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze OpenAI's writing signal \"Estimating worst case frontier risks of open weight LLMs\" for frontier lab strategy and data-business implications."},"semantic_triples":[{"subject":"OpenAI","predicate":"published","object":"Estimating worst case frontier risks of open weight LLMs","text":"OpenAI published Estimating worst case frontier risks of open weight LLMs."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"is classified as","object":"writing signal","text":"Estimating worst case frontier risks of open weight LLMs is classified as writing signal."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"belongs to","object":"talking desk","text":"Estimating worst case frontier risks of open weight LLMs belongs to talking desk."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Estimating worst case frontier risks of open weight LLMs has evidence coverage 1 captured evidence page."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"matches data-business lanes","object":"Safety and policy","text":"Estimating worst case frontier risks of open weight LLMs matches data-business lanes Safety and policy."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has captured page count","object":"1","text":"Estimating worst case frontier risks of open weight LLMs has captured page count 1."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has readable page count","object":"1","text":"Estimating worst case frontier risks of open weight LLMs has readable page count 1."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has related signal count","object":"6","text":"Estimating worst case frontier risks of open weight LLMs has related signal count 6."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has analysis playbook objective","object":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","text":"Estimating worst case frontier risks of open weight LLMs has analysis playbook objective Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has source host","object":"openai.com","text":"Estimating worst case frontier risks of open weight LLMs has source host openai.com."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has lab","object":"OpenAI","text":"Estimating worst case frontier risks of open weight LLMs has lab OpenAI."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has signal desk","object":"talking","text":"Estimating worst case frontier risks of open weight LLMs has signal desk talking."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has source host","object":"openai.com","text":"Estimating worst case frontier risks of open weight LLMs has source host openai.com."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has notability","object":"Notable risk analysis post from OpenAI","text":"Estimating worst case frontier risks of open weight LLMs has notability Notable risk analysis post from OpenAI."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has radar lane","object":"Safety and policy","text":"Estimating worst case frontier risks of open weight LLMs has radar lane Safety and policy."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has matched term","object":"security","text":"Estimating worst case frontier risks of open weight LLMs has matched term security."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has matched term","object":"risk","text":"Estimating worst case frontier risks of open weight LLMs has matched term risk."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has watch term","object":"RL environments","text":"Estimating worst case frontier risks of open weight LLMs has watch term RL environments."}]},"intelligence":{"signal_desk":"talking","answer":"OpenAI published Estimating worst case frontier risks of open weight LLMs. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Notable risk analysis post from OpenAI · Estimating worst case frontier risks of open weight LLMs | OpenAI August 5, 2025 Safety Publication Estimating worst case frontier risks of open weight LLMs Read the.... onlylabs links this event to 1 captured evidence page and 6 related writing signals. It also maps to Safety and policy in the data-business radar.","semantic_triples":[{"subject":"OpenAI","predicate":"published","object":"Estimating worst case frontier risks of open weight LLMs","text":"OpenAI published Estimating worst case frontier risks of open weight LLMs."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"is classified as","object":"writing signal","text":"Estimating worst case frontier risks of open weight LLMs is classified as writing signal."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"belongs to","object":"talking desk","text":"Estimating worst case frontier risks of open weight LLMs belongs to talking desk."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Estimating worst case frontier risks of open weight LLMs has evidence coverage 1 captured evidence page."},{"subject":"Estimating worst case frontier risks of open weight LLMs","predicate":"matches data-business lanes","object":"Safety and policy","text":"Estimating worst case frontier risks of open weight LLMs matches data-business lanes Safety and policy."}]},"signal":{"id":"3b406f1e-9801-4e8f-9632-4257d65926f0","url":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0","json_url":"https://onlylabs.fyi/signals/3b406f1e-9801-4e8f-9632-4257d65926f0/signal.json","source_url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","title":"Estimating worst case frontier risks of open weight LLMs","summary":"OpenAI published a writing signal. onlylabs watches public writing for research themes, product direction, and model-launch context.","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2025-08-05T00:00:00+00:00","first_seen_at":"2026-06-05T05:42:57.832854+00:00","date_source":"rss.item_date","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["exa"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms"]},"facets":{},"traction":{"github_stars":null,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":{"lanes":[{"key":"safety","label":"Safety and policy","url":"https://onlylabs.fyi/data-radar/safety"}],"score":15,"matched_terms":["security","risk"],"reason":"OpenAI has a writing signal matching safety and policy."}},"primary_evidence_page":{"url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","final_url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","title":"Estimating worst case frontier risks of open weight LLMs","http_status":200,"content_type":null,"capture_method":"exa","fetched_at":"2026-06-08T15:45:39.211+00:00","bytes":null,"raw_path":null,"content_hash":null,"excerpt_chars":1200,"truncated":true,"excerpt":"Estimating worst case frontier risks of open weight LLMs | OpenAI August 5, 2025 Safety Publication Estimating worst case frontier risks of open weight LLMs Read the paper Share Abstract In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity. To maximize biological risk (biorisk), we curate tasks related to threat creation and train gpt-oss in an RL environment with web browsing. To maximize cybersecurity risk, we train gpt-oss in an agentic coding environment to solve capture-the-flag (CTF) challenges. We compare these MFT models against open- and closed-weight LLMs on frontier risk evaluations. Compared to frontier closed-weight models, MFT gpt-oss underperforms OpenAI o3, a model that is below Preparedness High capability level for biorisk and cybersecurity. Compared to open-weight models, gpt-oss may marginally increase biological capabilities but does not substantially advance the frontier. Taken together, these results contributed to our decision to release the model, and..."},"evidence_pages":[{"url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","final_url":"https://openai.com/index/estimating-worst-case-frontier-risks-of-open-weight-llms","title":"Estimating worst case frontier risks of open weight LLMs","http_status":200,"content_type":null,"capture_method":"exa","fetched_at":"2026-06-08T15:45:39.211+00:00","bytes":null,"raw_path":null,"content_hash":null,"excerpt_chars":1200,"truncated":true,"excerpt":"Estimating worst case frontier risks of open weight LLMs | OpenAI August 5, 2025 Safety Publication Estimating worst case frontier risks of open weight LLMs Read the paper Share Abstract In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity. To maximize biological risk (biorisk), we curate tasks related to threat creation and train gpt-oss in an RL environment with web browsing. To maximize cybersecurity risk, we train gpt-oss in an agentic coding environment to solve capture-the-flag (CTF) challenges. We compare these MFT models against open- and closed-weight LLMs on frontier risk evaluations. Compared to frontier closed-weight models, MFT gpt-oss underperforms OpenAI o3, a model that is below Preparedness High capability level for biorisk and cybersecurity. Compared to open-weight models, gpt-oss may marginally increase biological capabilities but does not substantially advance the frontier. Taken together, these results contributed to our decision to release the model, and..."}],"related_signals":[{"id":"b3668d3b-26d2-40c0-9d4f-ed1a67927aa4","url":"https://onlylabs.fyi/signals/b3668d3b-26d2-40c0-9d4f-ed1a67927aa4","source_url":"https://openai.com/index/supporting-eu-trustworthy-ai-ecosystem","title":"Supporting Europe’s work in ensuring a trustworthy AI ecosystem ","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2026-06-11T00:00:00+00:00","first_seen_at":"2026-06-11T08:00:56.140796+00:00","date_source":"rss.item_date"},{"id":"2638c0a7-b372-409c-ac72-f6d81d6464dc","url":"https://onlylabs.fyi/signals/2638c0a7-b372-409c-ac72-f6d81d6464dc","source_url":"https://openai.com/index/using-codex-to-simulate-black-holes","title":"How an astrophysicist uses Codex to help simulate black holes","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2026-06-11T00:00:00+00:00","first_seen_at":"2026-06-11T07:01:16.936464+00:00","date_source":"rss.item_date"},{"id":"509ea784-51ec-4ede-855b-5a4d1b27d3be","url":"https://onlylabs.fyi/signals/509ea784-51ec-4ede-855b-5a4d1b27d3be","source_url":"https://openai.com/index/openai-on-oracle-cloud","title":"Access OpenAI models and Codex through your Oracle cloud commitment","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2026-06-10T20:00:00+00:00","first_seen_at":"2026-06-11T07:01:16.936464+00:00","date_source":"rss.item_date"},{"id":"4f051449-87f2-466e-941e-b5918381a8fe","url":"https://onlylabs.fyi/signals/4f051449-87f2-466e-941e-b5918381a8fe","source_url":"https://openai.com/index/prc-linked-influence-operations-ai-debates","title":"PRC-linked influence operations are targeting AI debates in the US","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2026-06-10T12:00:00+00:00","first_seen_at":"2026-06-11T07:01:16.936464+00:00","date_source":"rss.item_date"},{"id":"4507c0c1-cb74-4bb3-b62b-5f6c2d37e20d","url":"https://onlylabs.fyi/signals/4507c0c1-cb74-4bb3-b62b-5f6c2d37e20d","source_url":"https://openai.com/index/lseg","title":"From data to decisions: how LSEG is scaling trusted AI","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2026-06-10T00:00:00+00:00","first_seen_at":"2026-06-10T09:18:54.26094+00:00","date_source":"rss.item_date"},{"id":"fb16aa7a-c4ef-4859-b514-0839c2f1330d","url":"https://onlylabs.fyi/signals/fb16aa7a-c4ef-4859-b514-0839c2f1330d","source_url":"https://openai.com/index/nextdoor","title":"How engineers at Nextdoor use Codex to build without limits","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"openai","name":"OpenAI","category":"frontier-lab"},"occurred_at":"2026-06-09T12:00:00+00:00","first_seen_at":"2026-06-10T07:01:28.700378+00:00","date_source":"rss.item_date"}]}