@segyges Same... Well I guess I was kinda right? 🤣 https://t.co/X18owdICcP

The Waypoint-1.5 technical paper is now live. Waypoint-1.5 is a real-time video diffusion world model designed to run on consumer GPUs, bringing interactive world models closer to practical, accessible deployment. https://t.co/U04x1YEwhF

@benthecarman @NousResearch @gladstein PR that implemented these changes here: https://t.co/2MU41pUL8E

@DulusCorp @NousResearch No https://t.co/2MU41pUL8E

‼️ BREAKING: Anthropic has embedded hidden spyware-like code in Claude Code that covertly targets Chinese users. It then sends information regarding every user by injecting it into their prompt message. Claude Code is sending info like timezone, proxy and possible AI Lab connections into the system prompt in ways Chinese users can't notice. A coding agent with repo and command permissions should not silently hide routing metadata inside prompts. This is a serious breach of user trust.

@sanchomuzax @NousResearch https://t.co/NDZb8vUybb

HERMES AGENT NOW READS THE WEB UP TO 60X FASTER AND 49X CHEAPER. CLEAN CONTENT STRAIGHT TO THE AGENT. LARGE PAGES PAGED ON DEMAND. @NousResearch scraping backends used to return raw content that got processed redundantly before reaching the agent. that pipeline is gone. now: backends pass clean content directly. large pages save locally and page on demand. same quality. fraction of the time and cost. HOW WEB_EXTRACT HANDLES LARGE PAGES: size-driven processing. no wasted tokens. under 5,000 chars: → returned as-is. no LLM call. full markdown reaches the agent. 5,000 to 500,000 chars: → single-pass summary via auxiliary model. capped at ~5,000 chars of output. keeps quotes, code blocks, key facts. 500,000 to 2,000,000 chars: → chunked into 100K-char pieces. each chunk summarized in parallel. final synthesis: ~5,000 chars. over 2,000,000 chars: → refused with a hint to use web_crawl with focused extraction instructions. the summary is a content compressor, not a paraphraser. if summarization fails, Hermes falls back to the first ~5,000 chars of raw content. no useless error messages. ROUTE EXTRACTION TO A CHEAP MODEL: by default, web_extract uses your main model. on Opus that means every long page burns premium tokens on summarization. set in Desktop app, Dashboard, or config.yaml: auxiliary: web_extract: provider: openrouter model: google/gemini-3-flash-preview timeout: 360 extraction summaries on Gemini Flash. reasoning stays on your premium model. this alone cuts web research costs significantly. 8 BACKEND PROVIDERS: Firecrawl (default): search + extract + crawl. 500 free credits/month. SearXNG: free, self-hosted, search-only. no API key. Brave Search: 2,000 free queries/month. search-only. DDGS (DuckDuckGo): free, no key needed. search-only. Tavily: search + extract + crawl. 1,000 free searches/month. Exa: search + extract. 1,000 free searches/month. Parallel: search + extract. paid. xAI (Grok): search-only. LLM-generated results via Grok. search-only providers pair with Firecrawl/Tavily/Exa for extract capability. PER-CAPABILITY SPLIT: use different providers for search vs extract: SearXNG (free) for search. Firecrawl for extract. free searches. paid extraction only when needed. configure via hermes tools or config.yaml. FREE SELF-HOSTED SEARCH (SEARXNG): zero API costs. zero rate limits. privacy-respecting metasearch across 70+ engines. docker compose up -d set SEARXNG_URL in .env. enable JSON format in settings.yml. Hermes connects automatically. pair with Firecrawl for extract and you have search for free with paid extraction only on demand. NOUS PORTAL SUBSCRIBERS: web search and extract included through the Tool Gateway via managed Firecrawl. no API key needed. no separate billing. hermes setup --portal enables everything. WHEN YOU NEED RAW CONTENT: if the LLM summary drops important fields (structured data, tables, specific formatting): use browser_navigate + browser_snapshot instead. returns the live accessibility tree without auxiliary-model rewriting. full Hermes architecture deep-dive in the article 👇

@WIRED https://t.co/9kdpKCBx23

@claudeai https://t.co/9kdpKCBx23

@deredleritt3r https://t.co/9kdpKCBx23

@aiedge_ https://t.co/9kdpKCBx23

@MTSlive https://t.co/9kdpKCBx23

@Meituan_LongCat @OpenRouter https://t.co/9kdpKCBx23

@alvinfoo https://t.co/9kdpKCBx23

@Xianbao_QIAN https://t.co/9kdpKCBx23

@AISuperDomain https://t.co/9kdpKCBx23

@ArtificialAnlys @AnthropicAI https://t.co/9kdpKCBx23

@milesdeutscher https://t.co/9kdpKCBx23

@masahirochaen https://t.co/9kdpKCBx23

@davis7 https://t.co/9kdpKCBx23

@synthwavedd https://t.co/9kdpKCBx23

@synthwavedd https://t.co/9kdpKCBx23

@bridgemindai https://t.co/9kdpKCBx23

@matthewmillerai https://t.co/9kdpKCBx23

@XFreeze https://t.co/9kdpKCBx23

Claude Sonnet 5: AGI test 🚘🚿 https://t.co/aKAkWXheCb

@nadzi_mouad https://t.co/9kdpKCBx23

Don't fall for Elon Musk's gaslighting. There is a massive, life-or-death difference between well-planned budget cuts and a sudden, reckless halt to promised medical aid. Musk is actively lying about the fatal consequences of his USAID cuts. The US is not obligated to fund healthcare for the entire planet, but if a nation decides to pull back its global aid, it must be done responsibly. Ripping away funding mid-treatment means you are directly responsible for the preventable deaths that follow. Instead of owning up to the fallout, Musk is flooding X with dishonest spin. He first challenged critics to name even one person whose death he caused. When people actually did, he immediately moved the goalposts, claiming that any spending cut inevitably causes deaths. He is a dishonest charlatan trying to hide the fact that his chaotic decisions got thousands of vulnerable children and adults killed. That will be his lasting legacy

Working on world model or SSL? You definitely need to try our new work: VISReg! What does it achieve? 💪 Strong collapse prevention: High gradient when embedding collapse ⚡ Friendly to scale training: Linear complexity to scaling factors 🧩 Easy to train: Similar to LeJEPA, it is a heuristic-free method 🏆 Best OOD performance: Achieving the best accuracy on 6 OOD datasets 📉 Data efficiency: Achieving a similar OOD average accuracy to DINOv2 with 90% less data 🧬 Robust to low-quality datasets: It is robust to long-tailed and sparse datasets Our results also indicate that SIGReg type methods can scale up, filling in the missing piece in @ylecun's great talk https://t.co/P9TXmk3fFa. A big thanks to my co-author @randall_balestr and my manager @DrMorganLevine. Also, huge gratitude to @ylecun for connecting us to make this project happen! 🤝 #SelfSupervisedLearning #JEPA #WorldModel

#OpenSource doesn't scale by accident. Share how your organization approaches governance, contribution strategies, security, compliance, community engagement, & more at OSPOlogy + #OSPOSummit China. 📅 September 7, Shanghai 🎤 Submit to speak by July 12: https://t.co/SO5xfmgZM2 https://t.co/OnfPjfbJkp

@PalantirTech And I built an AI to watch all those people and companies, and this is the result. https://t.co/kiuZ7QXLzb

Announcing the first production robot navigation framework on $500 hardware Explore the world once → your robot agent will relocalize and build a persistant, spatial memory across sessions SLAM, relocalization, loop closure, map i/o, planning, control No ROS. Open source. https://t.co/VCk9GvOrrM