ai TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.
O shit I have to update my spooky movie list. Have you seen this one (re:zombies)?
Good overview of what the new Jev model is and how it's different from traditional LLM. com/jev/ Learn how Jev turns text into typed choices, scores, and probabilities, with JavaScript examples, practical patterns, limits, and real use cases.
Science Is Open Software L: https:// jepedersen.dk/blog/202505_rese arch/ C: https:// news.ycombinator.com/item?id=4 9762687 posted on 2026.09.18 at 22:21:35 (c=1, p=3)
I found it strange that Jev, the 'system one mode' by TypeSafe AI isn't... Typesafe?
Introducing System One Models and Jev view on hacker news Posted by albelfio with a score of 1394
"The bottleneck isn't raw intelligence.
OpenAI led an open letter signed by more than 100 organizations, including Anthropic, Microsoft, Google, Amazon, and others, on August 27–29, 2026, calling for coordinated defense against rising AI-enabled cyberattacks. Nvidia's new safety platform received cautious praise by November 2026, with experts noting no single solution exists to AI security risks.
Jev: New frontier model 40-400x cheaper and 20-200x faster. 15 a.
TypeSafe AI's Jev, built by a former OpenAI researcher, went viral on September 25, 2026, as a cheaper and faster alternative to large language models. The model lacks a chat interface but is marketed as a cost-effective competitor to OpenAI and Anthropic.
The programmer’s name was Jev Jevty Jev, and he was born on the first of Jev, Nineteen Jevty Jev Last week TypeSafe AI unveiled Jev, their first example of a new category of model that they are calling “System One models” (I’m with Maggie Appleton, I think “decision models” …
Of course the dude who "built Jev" (who was part of creating the ponzi scheme that is OpenAI) kind of, um, stole the whole thing. com/ Evaluates typed decisions (choice, score, noul) over 100+ languages in a single forward pass with calibrated probabilities.
Leaked CAD renders from August 24–25, 2026, suggest Samsung's upcoming Galaxy S27 Ultra will feature a redesigned wide rear camera plateau. Anthropic linked Claude's memory system between chat and Cowork on August 25, 2026. Separate reports cover systemd SSD damage claims, Thai flooding, kelvin wave ocean phenomena, and NRC workforce assessments.
The AI sector continued rapid expansion through September 2026, with Bloomberg reporting a $6 trillion revenue target needed by 2031 to justify data center investments. Women comprised only 26% of AI company hires according to LinkedIn research; concerns about AI agent safety were discussed in a White House meeting involving President Trump and tech executives on 2026-09-28.
Two separate social media posts about technical tools and research: an arXiv paper on certified multi-source integrity for structured agent actions, and a Mastodon post about the jev-harness TypeScript library. No single coherent story connects these fragments.
com. Follow @SidneyCur so you don't miss the next one.