STE80 Humanizer is an agent skill that rewrites AI-generated text for readability while aiming to preserve its meaning and facts. It combines two passes: first, it removes 26 common “AI tells,” such as staged openings, forced contrasts, dramatic closing lines, and excessive dashes; second, it restructures sentences using principles from ASD-STE100, the controlled English standard developed for aerospace maintenance documentation. The second pass favors short sentences, one idea at a time, active voice, simple tenses, and focused paragraphs. The default targets roughly 80% of the standard’s strictness, retaining ordinary words and natural phrasing rather than making prose sound like a manual.
The README argues that removing conspicuous phrases alone is not enough: text can use cleaner words and still bury several ideas in long, passive, hedged sentences. The tool therefore offers default humanizing, a lighter-touch mode, and strict STE for procedures or safety notes. It also claims to prioritize fidelity: preserve facts and qualifications, add nothing, and flag contradictions; users can provide a writing sample so rewrites better match their voice. It is designed for coding and writing agents including Claude Code, Codex, and Cursor, and can be installed through Skills.sh or as a Claude plugin. Its stated goal is easier-to-read writing, not evading AI detectors.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Researchers tested 16 LLMs on all 55 TIS-100 puzzles, giving each one attempt and time to refine its code. The models found 133 new performance tradeoffs across 18 puzzles and set three outright cycle records, though human players improved on most solutions within days. (tis-100.wincon.dev)
Australia is considering a new criminal offence for AI companies that fail to take reasonable steps to prevent harm caused by their models. The government is also weighing an AI safety watchdog with power to impose significant fines, following a hack of a Medicare statistics portal involving OpenAI. (abc.net.au)
AI is increasingly becoming a gateway through which people find information. Audiences still resist having AI produce their news. (niemanlab.org)
Nvidia holds a central position in the AI industry, making disruption to the company potentially catastrophic for the wider ecosystem. The race for advanced AI is also intensifying economic and geopolitical conflict, while concentrated corporate power and infrastructure face growing political resistance. (france24.com)
LLM inference can require reading about 26 GB of model weights to generate each token from a 13-billion-parameter model. The explanation shows how model size drives memory bandwidth demands during text generation. (youtube.com)
Deletion Tuning matches full fine-tuning across three LLM post-training methods by zeroing fewer than 0.05% of model weights. Its compact masks also preserve prior-task accuracy better than full fine-tuning, LoRA, and random sparse tuning. (arxiv.org)
Today's best Hacker News stories, summarized and screenshotted, one email a day.