A Push on Tactile Data, and a Warning That the Benchmark Was Leaking
A new tactile sensing benchmark called TouchEnables was found to have data leakage issues, where training and test sets overlapped, inflating performance results. The incident highlights growing concerns about data integrity in the tactile sensing and robotics research community.
Background
- The article covers a new benchmark to measure how well AI systems (particularly robots) understand tactile (touch) data. This is a growing field: most AI benchmarks test vision or language, but physical interaction remains hard to evaluate.
- The "benchmark leaking" problem: if a benchmark's test data is accidentally or intentionally exposed during training, the AI can "cheat" by memorizing answers rather than genuinely solving the task. This has plagued many AI benchmarks (e.g., image classification, language models).
- The piece warns that the tactile benchmark itself may have leaked, meaning its scores might overstate progress. This is a recurring issue in AI research — benchmarks often drive competition, so integrity matters.
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.