Survival LLM is a free, open-source AI assistant and reference library designed to remain usable when the internet is unavailable. It runs on a Mac or Windows computer, keeps questions and personal files on that device, and cites the material behind each answer, with links that highlight the relevant passage. Its offline library includes emergency and medical guidance from sources such as FEMA’s Ready.gov, the CDC, MedlinePlus, and WikEM, along with survival manuals, repair and how-to guides, and roughly 930,000 Wikipedia articles. Users can also add PDFs, documents, ebooks, and notes for the assistant to search, such as a generator manual or family emergency plan.
The app selects an AI model based on the computer’s memory; larger models require more storage but performed better in a blind test of 22 blackout and first-aid questions. The tested models scored from 14 to 21 answers judged to capture official guidance correctly, and the creators caution that AI can still be wrong, especially on smaller models - so checking the cited references matters. Setup requires an internet connection to download the model and library, then the software works offline. The full library download is 9 GB, or 1.3 GB without Wikipedia and iFixit; installation takes about 20 minutes to 2½ hours, mostly downloading. Supported systems are Apple Silicon Macs running macOS 14 or later and 64-bit Windows 10 or 11.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Trump said he would ban the term “artificial intelligence” in official documents and other materials. He wants it replaced with “super intelligence,” which he calls a more accurate name. (reuters.com)
New records show Medicare’s WISeR AI prior-authorization program has caused care delays, denials, operational problems, and reported patient harm. The EFF says the findings highlight the need for stronger legal limits on government use of automated decisions. (eff.org)
Anthropic expanded its GSA agreement, offering government agencies a 40% discount on Claude products and implementation support, with no minimum spending requirement. The deal extends to state, local, tribal, and territorial governments and is estimated to save the government $1 billion. (anthropic.com)
Anthropic has partnered with six biotech organizations and launched its own drug discovery programs to test Claude across the drug development process, from research and molecule design to clinical trials. The work has identified model improvements and could contribute to treatments for food allergies, childhood diseases, and cancers. (anthropic.com)
The supplied page contains no article text, so it provides no details to support the headline’s claim that China’s AI bubble has burst. The reasons and evidence behind that claim are unavailable. (finance.yahoo.com)
President Donald Trump says he will ban the term “artificial intelligence.” He wants the technology called “synthetic intelligence” instead. (thehill.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.