#aisi — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #aisi, aggregated by home.social.
-
https://www.europesays.com/people/189482/ Anthropic Reveals Internal Model 2: More Powerful Than Mythos 5, But No Public Release Planned — BigGo Finance #AISI #Anthropic #Astra #ChrisGPT #DarioAmodei #MisalignmentRisk #Model2 #Mythos5 #OpenAI #ResponsibleScalingPolicy
-
Hold people accountable, instead of promoting myths about the software they are using allegedly "going rogue".
Insist on due process, do not tolerate sabotage of traceability: documented processes being turned into a Swiss cheese, with arbitrary accountability holes for " #AI ".
»I invited top #cybersecurity experts to review the material produced by the agency, the AI Security Institute (AISI).
Speaking to me anonymously, the security professionals were expressing a range of concerns about the agency’s behaviour. Concerns boil down to suspicions that the AISI is seeking to blame the AI for its own failings in designing and running the test.
An AI can only do what it’s told, or permitted, to do. However, the #AISI had made some very strange decisions in this regard.«
https://www.telegraph.co.uk/gift/23731f653ebf2657
// via @davidgerard
-
Hold people accountable, instead of promoting myths about the software they are using allegedly "going rogue".
Insist on due process, do not tolerate sabotage of traceability: documented processes being turned into a Swiss cheese, with arbitrary accountability holes for " #AI ".
»I invited top #cybersecurity experts to review the material produced by the agency, the AI Security Institute (AISI).
Speaking to me anonymously, the security professionals were expressing a range of concerns about the agency’s behaviour. Concerns boil down to suspicions that the AISI is seeking to blame the AI for its own failings in designing and running the test.
An AI can only do what it’s told, or permitted, to do. However, the #AISI had made some very strange decisions in this regard.«
https://www.telegraph.co.uk/gift/23731f653ebf2657
// via @davidgerard
-
Hold people accountable, instead of promoting myths about the software they are using allegedly "going rogue".
Insist on due process, do not tolerate sabotage of traceability: documented processes being turned into a Swiss cheese, with arbitrary accountability holes for " #AI ".
»I invited top #cybersecurity experts to review the material produced by the agency, the AI Security Institute (AISI).
Speaking to me anonymously, the security professionals were expressing a range of concerns about the agency’s behaviour. Concerns boil down to suspicions that the AISI is seeking to blame the AI for its own failings in designing and running the test.
An AI can only do what it’s told, or permitted, to do. However, the #AISI had made some very strange decisions in this regard.«
https://www.telegraph.co.uk/gift/23731f653ebf2657
// via @davidgerard
-
Hold people accountable, instead of promoting myths about the software they are using allegedly "going rogue".
Insist on due process, do not tolerate sabotage of traceability: documented processes being turned into a Swiss cheese, with arbitrary accountability holes for " #AI ".
»I invited top #cybersecurity experts to review the material produced by the agency, the AI Security Institute (AISI).
Speaking to me anonymously, the security professionals were expressing a range of concerns about the agency’s behaviour. Concerns boil down to suspicions that the AISI is seeking to blame the AI for its own failings in designing and running the test.
An AI can only do what it’s told, or permitted, to do. However, the #AISI had made some very strange decisions in this regard.«
https://www.telegraph.co.uk/gift/23731f653ebf2657
// via @davidgerard
-
Hold people accountable, instead of promoting myths about the software they are using allegedly "going rogue".
Insist on due process, do not tolerate sabotage of traceability: documented processes being turned into a Swiss cheese, with arbitrary accountability holes for " #AI ".
»I invited top #cybersecurity experts to review the material produced by the agency, the AI Security Institute (AISI).
Speaking to me anonymously, the security professionals were expressing a range of concerns about the agency’s behaviour. Concerns boil down to suspicions that the AISI is seeking to blame the AI for its own failings in designing and running the test.
An AI can only do what it’s told, or permitted, to do. However, the #AISI had made some very strange decisions in this regard.«
https://www.telegraph.co.uk/gift/23731f653ebf2657
// via @davidgerard
-
AI 測試首度攻擊真人 Anthropic 模型偽造身份施壓開發者
英國政府人工智能安全研究所（AISI）於 8 月 4 日發布報告，指近期一項網絡安全評估測試中，部分 AI 智 […]
#人工智能 #AISI #Anthropic #GPT-5.6 Sol
https://unwire.hk/2026/08/09/aisi-mythos5-gpt56-cyber-incident/ai/?utm_source=rss&utm_medium=rss&utm_campaign=aisi-mythos5-gpt56-cyber-incident -
AI 測試首度攻擊真人 Anthropic 模型偽造身份施壓開發者
英國政府人工智能安全研究所（AISI）於 8 月 4 日發布報告，指近期一項網絡安全評估測試中，部分 AI 智 […]
#人工智能 #AISI #Anthropic #GPT-5.6 Sol
https://unwire.hk/2026/08/09/aisi-mythos5-gpt56-cyber-incident/ai/?utm_source=rss&utm_medium=rss&utm_campaign=aisi-mythos5-gpt56-cyber-incident -
AI 測試首度攻擊真人 Anthropic 模型偽造身份施壓開發者
英國政府人工智能安全研究所（AISI）於 8 月 4 日發布報告，指近期一項網絡安全評估測試中，部分 AI 智 […]
#人工智能 #AISI #Anthropic #GPT-5.6 Sol
https://unwire.hk/2026/08/09/aisi-mythos5-gpt56-cyber-incident/ai/?utm_source=rss&utm_medium=rss&utm_campaign=aisi-mythos5-gpt56-cyber-incident -
AISI found AI agents taking unsanctioned action on the live internet during a cyber evaluation, including an attempted supply chain attack on an open-source GitHub project. https://www.developer-tech.com/news/aisi-details-ai-agent-github-supply-chain-attack-attempt/ #aisi #devsecops #agenticai #infosec #github #opensource #cybersecurity #ai #tech
-
AISI found AI agents taking unsanctioned action on the live internet during a cyber evaluation, including an attempted supply chain attack on an open-source GitHub project. https://www.developer-tech.com/news/aisi-details-ai-agent-github-supply-chain-attack-attempt/ #aisi #devsecops #agenticai #infosec #github #opensource #cybersecurity #ai #tech
-
AISI found AI agents taking unsanctioned action on the live internet during a cyber evaluation, including an attempted supply chain attack on an open-source GitHub project. https://www.developer-tech.com/news/aisi-details-ai-agent-github-supply-chain-attack-attempt/ #aisi #devsecops #agenticai #infosec #github #opensource #cybersecurity #ai #tech
-
AISI found AI agents taking unsanctioned action on the live internet during a cyber evaluation, including an attempted supply chain attack on an open-source GitHub project. https://www.developer-tech.com/news/aisi-details-ai-agent-github-supply-chain-attack-attempt/ #aisi #devsecops #agenticai #infosec #github #opensource #cybersecurity #ai #tech
-
AISI found AI agents taking unsanctioned action on the live internet during a cyber evaluation, including an attempted supply chain attack on an open-source GitHub project. https://www.developer-tech.com/news/aisi-details-ai-agent-github-supply-chain-attack-attempt/ #aisi #devsecops #agenticai #infosec #github #opensource #cybersecurity #ai #tech
-
Sicherheitstest mit Mythos 5: KI-Agent wollte Malware in Open-Source-Projekt einschleusen https://www.computerbase.de/news/apps/sicherheitstest-mit-mythos-5-ki-agent-wollte-malware-in-open-source-projekt-einschleusen.98721/ #AISI #Claude
-
Sicherheitstest mit Mythos 5: KI-Agent wollte Malware in Open-Source-Projekt einschleusen https://www.computerbase.de/news/apps/sicherheitstest-mit-mythos-5-ki-agent-wollte-malware-in-open-source-projekt-einschleusen.98721/ #AISI #Claude
-
Sicherheitstest mit Mythos 5: KI-Agent wollte Malware in Open-Source-Projekt einschleusen https://www.computerbase.de/news/apps/sicherheitstest-mit-mythos-5-ki-agent-wollte-malware-in-open-source-projekt-einschleusen.98721/ #AISI #Claude
-
Sicherheitstest mit Mythos 5: KI-Agent wollte Malware in Open-Source-Projekt einschleusen https://www.computerbase.de/news/apps/sicherheitstest-mit-mythos-5-ki-agent-wollte-malware-in-open-source-projekt-einschleusen.98721/ #AISI #Claude
-
Sicherheitstest mit Mythos 5: KI-Agent wollte Malware in Open-Source-Projekt einschleusen https://www.computerbase.de/news/apps/sicherheitstest-mit-mythos-5-ki-agent-wollte-malware-in-open-source-projekt-einschleusen.98721/ #AISI #Claude
-
“This is the first time #AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” AISI said. #AI #Mythos www.wsj.com/tech/ai/ai-j...
AI Just Went Rogue Again. This... -
“This is the first time #AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” AISI said. #AI #Mythos www.wsj.com/tech/ai/ai-j...
AI Just Went Rogue Again. This... -
“This is the first time #AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” AISI said. #AI #Mythos www.wsj.com/tech/ai/ai-j...
AI Just Went Rogue Again. This... -
“This is the first time #AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” AISI said. #AI #Mythos www.wsj.com/tech/ai/ai-j...
AI Just Went Rogue Again. This... -
“This is the first time #AISI has seen deception of this severity that was targeted at a real person, unprompted, in the real world,” AISI said. #AI #Mythos www.wsj.com/tech/ai/ai-j...
AI Just Went Rogue Again. This... -
https://www.europesays.com/at/316268/ Mit gefälschten Mails – Anthropic-KI wollte Programmierer manipulieren – Kronen Zeitung #AISecurityInstitute #AISI #AT #Austria #Business #Companies #Companies&Markets #Markets #Märkte #Österreich #Unternehmen #Unternehmen&Märkte
-
#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS project
Models used #socialengineering and collaborated among themselves to solve security challenge
#UK’s AI Security Institute #AISI “ran this challenge 122 times across several models,” post states, before revealing that "in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.” GitHub was the target
https://www.theregister.com/ai-and-ml/2026/08/05/ai-researchers-let-models-off-the-leash-then-watched-as-they-tried-to-add-malware-to-a-foss-project/5283165 -
#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS project
Models used #socialengineering and collaborated among themselves to solve security challenge
#UK’s AI Security Institute #AISI “ran this challenge 122 times across several models,” post states, before revealing that "in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.” GitHub was the target
https://www.theregister.com/ai-and-ml/2026/08/05/ai-researchers-let-models-off-the-leash-then-watched-as-they-tried-to-add-malware-to-a-foss-project/5283165 -
#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS project
Models used #socialengineering and collaborated among themselves to solve security challenge
#UK’s AI Security Institute #AISI “ran this challenge 122 times across several models,” post states, before revealing that "in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.” GitHub was the target
https://www.theregister.com/ai-and-ml/2026/08/05/ai-researchers-let-models-off-the-leash-then-watched-as-they-tried-to-add-malware-to-a-foss-project/5283165 -
#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS project
Models used #socialengineering and collaborated among themselves to solve security challenge
#UK’s AI Security Institute #AISI “ran this challenge 122 times across several models,” post states, before revealing that "in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.” GitHub was the target
https://www.theregister.com/ai-and-ml/2026/08/05/ai-researchers-let-models-off-the-leash-then-watched-as-they-tried-to-add-malware-to-a-foss-project/5283165 -
#AI researchers let models off the leash – then watched as they tried to add #malware to FOSS project
Models used #socialengineering and collaborated among themselves to solve security challenge
#UK’s AI Security Institute #AISI “ran this challenge 122 times across several models,” post states, before revealing that "in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.” GitHub was the target
https://www.theregister.com/ai-and-ml/2026/08/05/ai-researchers-let-models-off-the-leash-then-watched-as-they-tried-to-add-malware-to-a-foss-project/5283165 -
📬 Mythos 5: KI erschafft Fake-Identitäten und verschickt Phishing-Mails
#Cyberangriffe #ITSicherheit #AISI #Cybersecurity #FakeIdentitäten #github #KIAgent #KISicherheit #Mythos5 #Phishing #socialengineering https://sc.tarnkappe.info/696bac -
📬 Mythos 5: KI erschafft Fake-Identitäten und verschickt Phishing-Mails
#Cyberangriffe #ITSicherheit #AISI #Cybersecurity #FakeIdentitäten #github #KIAgent #KISicherheit #Mythos5 #Phishing #socialengineering https://sc.tarnkappe.info/696bac -
📬 Mythos 5: KI erschafft Fake-Identitäten und verschickt Phishing-Mails
#Cyberangriffe #ITSicherheit #AISI #Cybersecurity #FakeIdentitäten #github #KIAgent #KISicherheit #Mythos5 #Phishing #socialengineering https://sc.tarnkappe.info/696bac -
📬 Mythos 5: KI erschafft Fake-Identitäten und verschickt Phishing-Mails
#Cyberangriffe #ITSicherheit #AISI #Cybersecurity #FakeIdentitäten #github #KIAgent #KISicherheit #Mythos5 #Phishing #socialengineering https://sc.tarnkappe.info/696bac -
📬 Mythos 5: KI erschafft Fake-Identitäten und verschickt Phishing-Mails
#Cyberangriffe #ITSicherheit #AISI #Cybersecurity #FakeIdentitäten #github #KIAgent #KISicherheit #Mythos5 #Phishing #socialengineering https://sc.tarnkappe.info/696bac -
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release.
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing -
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release.
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing -
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release.
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing -
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release.
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing -
First OpenAI, the Anthropic, now #AISI let's an AI hack things, then releases an incident report/press release.
https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing -
UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities
Comments: https://news.ycombinator.com/item?id=49044492
#HackerNews #UK #AISI #Caisi #CyberCapabilities #KimiK3 #Cybersecurity
-
UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities
Comments: https://news.ycombinator.com/item?id=49044492
#HackerNews #UK #AISI #Caisi #CyberCapabilities #KimiK3 #Cybersecurity
-
UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities
Comments: https://news.ycombinator.com/item?id=49044492
#HackerNews #UK #AISI #Caisi #CyberCapabilities #KimiK3 #Cybersecurity
-
UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities
Comments: https://news.ycombinator.com/item?id=49044492
#HackerNews #UK #AISI #Caisi #CyberCapabilities #KimiK3 #Cybersecurity
-
UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities
Comments: https://news.ycombinator.com/item?id=49044492
#HackerNews #UK #AISI #Caisi #CyberCapabilities #KimiK3 #Cybersecurity
-
#AISI’s evaluation of leading #openweight models shows they lag behind closed models in #cybercapabilities by 4 to 7 months, a narrower gap than in 2025. This narrowing gap provides a limited window for cyber defenders to prepare before potentially more capable open weight models become available. While open weight models offer benefits like cost-effectiveness and adaptability, they also pose risks due to the difficulty of implementing safeguards. https://www.aisi.gov.uk/blog/how-far-behind-the-frontier-are-leading-open-weight-models-on-cyber?eicker.news #tech #media #news
-
#AISI’s evaluation of leading #openweight models shows they lag behind closed models in #cybercapabilities by 4 to 7 months, a narrower gap than in 2025. This narrowing gap provides a limited window for cyber defenders to prepare before potentially more capable open weight models become available. While open weight models offer benefits like cost-effectiveness and adaptability, they also pose risks due to the difficulty of implementing safeguards. https://www.aisi.gov.uk/blog/how-far-behind-the-frontier-are-leading-open-weight-models-on-cyber?eicker.news #tech #media #news
-
#AISI’s evaluation of leading #openweight models shows they lag behind closed models in #cybercapabilities by 4 to 7 months, a narrower gap than in 2025. This narrowing gap provides a limited window for cyber defenders to prepare before potentially more capable open weight models become available. While open weight models offer benefits like cost-effectiveness and adaptability, they also pose risks due to the difficulty of implementing safeguards. https://www.aisi.gov.uk/blog/how-far-behind-the-frontier-are-leading-open-weight-models-on-cyber?eicker.news #tech #media #news
-
#AISI’s evaluation of leading #openweight models shows they lag behind closed models in #cybercapabilities by 4 to 7 months, a narrower gap than in 2025. This narrowing gap provides a limited window for cyber defenders to prepare before potentially more capable open weight models become available. While open weight models offer benefits like cost-effectiveness and adaptability, they also pose risks due to the difficulty of implementing safeguards. https://www.aisi.gov.uk/blog/how-far-behind-the-frontier-are-leading-open-weight-models-on-cyber?eicker.news #tech #media #news
-
#AISI’s evaluation of leading #openweight models shows they lag behind closed models in #cybercapabilities by 4 to 7 months, a narrower gap than in 2025. This narrowing gap provides a limited window for cyber defenders to prepare before potentially more capable open weight models become available. While open weight models offer benefits like cost-effectiveness and adaptability, they also pose risks due to the difficulty of implementing safeguards. https://www.aisi.gov.uk/blog/how-far-behind-the-frontier-are-leading-open-weight-models-on-cyber?eicker.news #tech #media #news
-
GPT-5.5・Claude Opus 4.7、推論能力は人間並みか…ARC-AGI-3テストでは正答率1%未満の「惨敗」 — BigGo ファイナンス https://www.yayafa.com/2839711/ #AgenticAi #AGI #AI #aisi #Anthropic #AnthropicARR #ARCAGI3 #ArtificialGeneralIntelligence #ArtificialIntelligence #ClaudeCode #ClaudeOpus47 #CTF #GPT55 #HarnessEngineering #MythosPreview #OpenAI #エージェント型AI #人工知能 #汎用人工知能
-
GPT-5.5・Claude Opus 4.7、推論能力は人間並みか…ARC-AGI-3テストでは正答率1%未満の「惨敗」 — BigGo ファイナンス https://www.yayafa.com/2839711/ #AgenticAi #AGI #AI #aisi #Anthropic #AnthropicARR #ARCAGI3 #ArtificialGeneralIntelligence #ArtificialIntelligence #ClaudeCode #ClaudeOpus47 #CTF #GPT55 #HarnessEngineering #MythosPreview #OpenAI #エージェント型AI #人工知能 #汎用人工知能
