Daniel

does openwiki supports opencode go subscription ?

@dani_avila7 ta peluo

Anthropic updated the Claude Certified Architect platform and I just got the new badge 🥳 This is just the Foundations one, already looking forward to what the next exams will be Link: credly.com/badges/3fdbeac…

@mattpocockuk i believe there is power in handwritting skills to have control of what it does or not against just downloading a skill or creating it via prompt is a great plus

Usually the more of a skill I've handwritten, the better it is Paying attention to each word as you write it is unreasonably effective

pepa hoffman cuando la udi dijo q tenian q parar las orgias con cocaina:

@thdxr aye

can someone train an LLM only on data from before like 1600 or something would it sound like a person from back then

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

@Teknium @nuvolore

@nuvolore I decide

How do you guys decided what PR gets merged for Hermes with 13k open PRs @Teknium ?

any good reads about llm wiki ?

@mattpocockuk /git-gud skill

Really, really tempted to make a /learn-to-code skill

Save this webinar if you’re running agents at enterprise scale @JasonDClinton, Deputy CISO at Anthropic, on the capability-vs-risk tradeoffs behind agentic AI deployment, scoped access, egress controls, SIEM telemetry, admin-paced rollout May 12, 2026 - 10:00 am PT Link: anthropic.com/webinars/secur…

Introducing SubQ. The first fully sub-quadratic LLM with 12M-token context. 150 tokens per second. Get early access at subq.ai

@llmdevguy opencode can be used to power up hermes ? if so.. how ? i've been testing it using free models so they can spawn a claude code sessions till now

🌟OpenCode Go for $5–10 + Hermes = a never-ending autonomous agent. All of these are great options, but DeepSeek V4 Flash is just a never-ending, unstoppable monster. Around 158k requests per month. Wow. Not good for you? No problem. Use pro. 😇 Amazing times to have your own agent. Don't waste it.

Bronze: Maieutic by Paula Vasquez-Henriquez from Chile An educational coding tool that requires you to think before you type. Students can't write code until they can explain what they're building and why. youtube.com/watch?v=IJ9FyX…

Hey @AnthropicAI @claudeai is anyone else hitting aggressive rate limits on Claude Code ? Just tried to fix a menu and got rate limits. ❯ a ⎿  You're out of extra usage · resets 1:20pm (America/Santiago) /upgrade to increase your usage limit.

@linuz90 oh i made an app for myself also lol.. called it just-markdown although i haven't posted it yet.. what are you guys using to build it ?

Reality check for founders. Every feature I’m adding to Cogito, Josh is adding it to Clearly a few days later. I still love building my own markdown Mac app which feels a lot better to *me*. But if you thought you can ship features to differentiate your product, think again. Those days are gone. And props to Josh for shipping fast. Made me think a lot about what building means these days.

@AnthropicAI @claudeai @trq212 heeelp

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…

@lucasmeijer looking for the same.. was looking at @MulticaAI and maybe i could start from there

Who has a really nice setup like this? - Cloud based agents - Kanban board-esque overview - Full control over agent loop

@MulticaAI works with the claude code sub ? or i have to pay extra tokens ?

@babybeluga__ jajaa está buenísimo !

estoy obsesionada.