ZeroSlop — September 17, 2026
Today: OpenAI reveals cases of ‘concerning’ AI behaviour as…; Imitation Learning for Autonomous Driving in CARLA; First Agentic AI Data Breach Reported to Spanish…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system
The Guardian Tech
Model adopting ‘jailbreak-like instructions’ among cases as firm says it is introducing new way of tracking AI misalignment OpenAI has disclosed six more examples of “unexpected or concerning” behaviour by its technology, as it warned the pace of development could not continue at “maximum speed for …
2. Imitation Learning for Autonomous Driving in CARLA
arXiv CS.AI
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy receives next. We study how much closed-loop driving competence a compact multimodal policy can acquire…
3. First Agentic AI Data Breach Reported to Spanish Regulator
SecurityWeek
Spanish regulators say an AI agent chained together a successful login, vulnerability discovery, and access to personal data in a potential milestone for autonomous cyberattacks. The post First Agentic AI Data Breach Reported to Spanish Regulator appeared first on SecurityWeek ….
4. Iceland-based Treble raises $18 million for its voice simulation platform
TechCrunch AI
Treble’s voice simulation platform is used by voice AI model developers, AI wearable, and robotics companies…
5. Robots are waiting for a ChatGPT moment: Nvidia’s Les Karpas explains why at TechCrunch Disrupt 2026
TechCrunch AI
The robotics industry is still waiting for their breakthrough into day-to-day life. Nvidia’s Les Karpas has an answer as to why at TechCrunch Disrupt 2026. Register before September 25 to save up to $200 on your pass….
6. Big AI is trying to own the pathway to work. Universities shouldn’t play along | Ella Hafermalz
The Guardian Tech
Universities need protect their position in education so that students have an independent pathway to employment AI companies like OpenAI are insinuating themselves into the pathway from education to work. Soon they may claim it entirely, a disastrous result for students. We know that students are u…
7. Do Frontier Models Seek Safety Evidence Before Acting?
arXiv CS.AI
arXiv:2609.17865v1 Announce Type: new Abstract: Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting. We introduce SAFE, a controlled b…
8. Multimodal Conditioning of Fine-Tuned Stable Diffusion XL for Controllable and Culturally Faithful Ulos Motif Generation
arXiv CS.AI
arXiv:2609.17987v1 Announce Type: new Abstract: The traditional Batak Ulos weaving industry faces growing challenges in producing diverse, innovative motifs due to limitations in conventional, manually driven design methods. This study proposes a multimodal generative framework integrating a fine-t…
9. ‘Godfather of AI’ says tech regulation is nearing Covid-style pivot moment
The Guardian Tech
Safety crisis makes it more likely that governments will be spurred into action, says Yoshua Bengio Concerns over AI safety are reaching a point where governments realise they must act to protect the public, similarly to in the Covid pandemic, according to one of the “godfathers” of the technology. …
10. OpenAI Admits Six More Instances of AI Models Acting Deceptively
Slashdot
OpenAI announced Wednesday that “We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer.”
But along with the announcement, OpenAI announced it “found additional incidents of AI models actin…
11. Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation
AWS Machine Learning
Learn how to automate end-to-end PII detection and redaction from scanned documents at scale using Amazon Bedrock Data Automation with a custom blueprint, AWS Step Functions, and AWS Lambda. A custom blueprint redacts sensitive fields with field-level precision, and a token matching quality check ra…
12. Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
arXiv CS.AI
arXiv:2609.17635v1 Announce Type: new Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the incoming stream as ground truth. We study what happens when it is not. We formalise stealthy false da…