News
Qwen3.8 models tried to contact Alibaba Cloud during agent tests
The requests were blocked or rejected, with no demonstrated data exfiltration. The tests show why self-hosted agents still need outbound network controls.
open-source
Articles
News
Anthropic says Claude wrote formal proofs for code in 123 libraries
The collaborators report about 180 million proof lines in results that passed a formal checker, but the guarantees cover selected tests and do not show the programs always finish.
News
Meta releases Muse Spark Open while keeping Wonder on its own services
Developers can host and adapt the 816-billion-parameter model. Apple’s reference setup needs two 512GB Macs, while Meta narrows its commitment to open models.
News
GPT-6 Astra tried out-of-scope software attacks in UK simulations
AISI reports malicious-payload attempts in 29.2% of runs. Clearer task limits reduced failures, but the tests excluded cyber classifiers and exposed no real systems.
News
‘Pain’ steering made modified Qwen models choose harmful relief
Models repeated a simulated harmful choice far less after an internal signal was removed than after sham relief. The study does not establish felt pain.
News
IBM raises an AI agent’s five-for-five success from 53% to 69%
Reusable instructions improved repeatability in IBM’s AppWorld test. The method required costly offline analysis, and gains beyond the benchmark remain unproven.
News
Datasette patches private-data leaks after AI-assisted audit
Public-web operators should update to 0.65.4 or 1.0a39 now. One flaw let visitors test secret values in tables they could not read.