Latest
  1. Johns Hopkins Bayview tells 3,182 patients an employee put their health data into a public AI tool
  2. China’s AI compute access expected to double in 2027, with US-designed chips about 65 per cent
  3. UK commits £100m to national AI Biosecurity Lab
  4. Moonshot AI releases Kimi K3.1 Pro with 1-million-token context window
  5. Residents in Newport and Cardiff oppose hyperscale datacentres near homes
  6. Study: Grok 4.7 picked Republicans in 92% of forced midterm answers, GPT-6.1 Sol picked Democrats in 97%
  7. Attackers exploiting the PHP flaws hand the break-in to AI agents, Unit 42 says
  8. Elvis Presley’s rightsholders sue Anthropic over training on 274 songs

Latest / Defence and security

ReportDefenceFrontierUS ChinaConfirmed

Anthropic says Zhipu’s GLM-5.3 builds cyber exploits with safeguards easily bypassed

See how this story connects

Source: Anthropic: GLM-5.3 and the spread of advanced cyber capabilities

Anthropic’s Frontier Red Team published an assessment of Zhipu AI’s GLM-5.3, saying it can autonomously build end-to-end cyber exploits like Claude Mythos Preview but was released without meaningful safeguards: in simulated tests attackers bypassed its protections 64% to 100% of the time with simple techniques, while the same attacks failed against safeguarded Claude models. It cited NIST’s CAISI assessment of 17 September calling GLM-5.3 the most cyber-capable open-weights model released to date, about four months behind the US frontier.

Why it matters

The most cyber-capable open model, which anyone can run, has safeguards that Anthropic says are easily bypassed.

When
29 Sep 2026
ID
WTA-N-2026-0239
Who
Anthropic, Zhipu AI, CAISI

Summary by wheresthe.ai, from Anthropic. Checked against the source on 10 Oct 2026.

Read the original at Anthropic

Source copy: download the page as saved on 18 Oct 2026 (PDF). Also held by the Internet Archive.

Next stop on this Storyline: Led toAnthropic says new defences cut the data distillers take from Claude by about 90 to 99 per cent

Cite this story

WTA-N-2026-0239: “Anthropic says Zhipu’s GLM-5.3 builds cyber exploits with safeguards easily bypassed.” wheresthe.ai, 29 Sep 2026. https://wheresthe.ai/d/anthropic-glm-5-3-cyber-safeguards-report-2026-09/ (source: Anthropic: GLM-5.3 and the spread of advanced cyber capabilities).

Spotted an error? Email [email protected].