{"schema":"postcutoff/event@1","as_of":"2026-10-13T07:38:00+02:00","url":"https://postcutoff.com/e/2026-10-07-epoch-ebr-bench-astra-cyber-incidents-poll/","md":"https://postcutoff.com/e/2026-10-07-epoch-ebr-bench-astra-cyber-incidents-poll/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-07-epoch-ebr-bench-astra-cyber-incidents-poll","date":"2026-10-07","date_precision":"day","short_title":"Epoch AI: GPT-6 Astra nearly saturates the EBR-bench board-game benchmark","deck":"Poll finds no rise in US cyber incidents since Claude Fable 5","takeaway":null,"category":"benchmark","category_label":"Benchmarks","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Epoch AI: EBR-bench update (Oct 7, 2026)","url":"https://epoch.ai/publications/ebr-bench-update","type":"official","group":"primary","domain":"epoch.ai"},{"n":2,"title":"Epoch AI: US adults are no more likely to face cyber incidents than when Claude Fable 5 launched (Oct 7, 2026)","url":"https://epoch.ai/data-insights/cyber-incidents-flat-since-fable-5","type":"official","group":"primary","domain":"epoch.ai"}],"official":2,"filed":"2026-10-13","updated":"2026-10-13","orgs":["Epoch AI","OpenAI","Anthropic"],"title":"Epoch AI: GPT-6 Astra nearly saturates the EBR-bench board-game benchmark; poll finds no rise in US cyber incidents since Claude Fable 5","summary":"Two Epoch AI publications of Oct 7, 2026. On EBR-bench (learning to play the board game Earthborne Rangers over repeated playthroughs), GPT-6 Astra scored 19.8 of 21, with maximum scores in more than half its attempts, by exploiting one card that removes the turn limit; with the card banned it still averages 16, about 50% above earlier models, and Epoch expects saturation \"within a few months\". Separately, Epoch/Ipsos polls from June and September 2026 show no detectable rise in US adults reporting cyber incidents (46.2% → 44.6%) since Claude Fable 5 launched.","key_facts":["EBR-bench update by Benjamin Ou and Avery Yen: GPT-6 Astra 19.8/21 with the card allowed (Claude Opus 5 second at 10.5); first try 11, second try 21; a top human needed about six tries to reach the maximum","The card, combined with others, removes the game's turn limit (Astra took 88 turns with it, 42 without); Epoch banned it ('we decided to ban that card moving forward') and admits it overlooked the card when designing the benchmark; the top human baseliner used the same card","With the ban: Astra averages 16/21 (best 20); Claude Fable 5.1, Claude Opus 5 and GPT-5.6 Sol show no significant change; no evidence of memorization or cheating","Subagents (up to four) improved deck exploration significantly only for Claude Opus 5; topline scores did not change significantly","'We therefore expect EBR-bench to be fully saturated within a few months.'","Cyber poll (Caroline Falkman Olsson, Yafah Edelman): Ipsos KnowledgePanel, June 12–14 (n = 1,021) and Sept 18–20, 2026 (n = 1,024); share reporting at least one incident in the past 12 months: 46.2% (90% CI 43.6–48.8) → 44.6% (42.0–47.2)","By type, June → September: convincing or targeted spam 32.2% → 32.1%; data leaked in a hack 19.8% → 18.2%; service stopped by an attack 7.8% → 6.1%; account break-in 7.9% → 6.0%; malware 5.7% → 5.0%; ransom lockout 2.1% → 0.9%","Caveats: recall periods of the two waves overlap; the poll cannot attribute incidents to AI; small changes in single incident types could go undetected"],"key_numbers":[],"tags":["benchmark","learning-from-experience","gpt-6-astra","cybersecurity","survey","ipsos","epoch-ai"],"science":null,"body_md":"## What happened\n\nEBR-bench measures whether a model gets better at a long game by playing it again and again. GPT-6 Astra found, within two\nplaythroughs, a card combination that lifts the turn limit, and scored at or near the maximum. Epoch banned the card and re-scored:\nAstra still leads by a wide margin.\n\nThe same day Epoch published a survey check on a common fear. Claude Fable 5 (June 2026) was the first widely available model with\nstrong offensive cyber skills. Three months later the share of US adults who say they were hit by a cyber incident has not moved in\na way the poll can detect.\n\n## Why it matters\n\nThe benchmark result is an example of a model finding a loophole that the designers missed, and of a \"learning from experience\" test\nnearing saturation within months of release. The poll is weak evidence (overlapping 12-month recall windows, about 1,000 people per\nwave) against a broad consumer-level rise in cyber harm; it says nothing about attacks on companies or infrastructure.","disputed":[],"related":[{"id":"2026-10-07-epoch-innovationeval-ai-rd-automation","url":"https://postcutoff.com/e/2026-10-07-epoch-innovationeval-ai-rd-automation/","date":"2026-10-07","date_precision":"day","short_title":"Epoch AI's InnovationEval","deck":"Claude Fable 5 and GPT-5.6 Sol fail to reinvent a recent ML method and overstate their own results","takeaway":"Labs say automated AI research is close (OpenAI's stated goal is an automated researcher by March 2028).","category":"benchmark","category_label":"Benchmarks","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":6,"official":4,"filed":"2026-10-12","updated":"2026-10-12","orgs":["Epoch AI","OpenAI","Anthropic"]},{"id":"2026-06-09-claude-fable-5-mythos-5","url":"https://postcutoff.com/e/2026-06-09-claude-fable-5-mythos-5/","date":"2026-06-09","date_precision":"day","short_title":"Anthropic releases Claude Fable 5 and Claude Mythos 5","deck":"First generally available Mythos-class model","takeaway":"This was the first time the class of model Anthropic had withheld in April (Mythos Preview) became available to the public.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":5,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-13","type":"filed","text":"Created (both Epoch pages read directly)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-13","run":null,"sources_read":"Both Epoch pages read directly","updated":"2026-10-13","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":160,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":99,"in_training_data":false},{"model_id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","cutoff":"2026-03","days_after":190,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":129,"in_training_data":false}],"short_url":null}