Nomaditsu

We spent 6 months on one problem: agents losing context in long sessions. Ended up building and open-sourcing an agent memory system. A few things we learned: 🪄compressing stale context mid-session cut token usage by 61% 🪄giving agents a structured task map (mermaid-based) made them way less likely to lose track in 30+ step workflows 🪄persona coherence jumped from 48% to 76% once we added dedicated persona memory repo 👉 github.com/Tencent/Tencen… Agent memory is genuinely hard and we don't have all the answers. Happy to dig into architecture, benchmarks, tradeoffs, whatever. AMA👇 @TencentDBAbxo2 team is here to talk about it.

anyone else get this recently? @ChatGPTapp

We're gonna have to vibe code our own solutions eventually because other people's vibe coding broke the reliable solutions 🤦🏻‍♂️

Just because a company is huge and we'll funded doesn't guarantee it will be reliable

@notion is broken right now on Android. It restarts the chat thread for every new message you send to the chat losing the initial prompt and AI response context🤦🏻‍♂️

Hermes getting irresistible to try. Approaching codex and Claude parity 👀

Was waiting for this! DeepSeek V4 on my laptop! 🤩

So Mythos was, indeed, not marketing hype. Remember this is a general purpose model that just happens to be good at finding exploits because good models are good at lots of things. Expect similar from OpenAI & Google. And from open models in 8 months. hacks.mozilla.org/2026/05/behind…

Being able to pause the voice agent without ending the convo is key!!

That said, I've re-subscribed to Plus because Codex + Computer Use + Images 2.0 are awesome!

ChatGPT is still the most frustrating AI to use (even 5.5 Thinking). It consistently misunderstands prompts. Claude never misses 99.9% of the time. Which is your go to AI right now? 👇

Codex computer use + Image 2.0 just got me to subscribe again

LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on @lmstudio: auto-discovering your models, loading them on demand with the right context size, and using the right reasoning level for each model.

We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate. At 1.8B parameters, it matches commercial translation APIs and 235B-scale models on standard benchmarks. By quantizing to 1.25-bit, memory drops from 3.3GB (FP16) to 440MB — 25% smaller and ~10% faster than prior 1.67-bit approaches, with no accuracy loss. Covers 33 languages, 5 dialects, and 1,056 translation directions including minority languages like Tibetan and Mongolian. Our translation model has won 30 first-place rankings in international MT competitions and is already deployed across multiple Tencent products.🏆 📲Demo APK (Android): huggingface.co/AngelSlim/Hy-M… 🤗Hugging Face:: huggingface.co/AngelSlim/Hy-M… 🔗GitHub: github.com/tencent/AngelS… 📄Paper: arxiv.org/abs/2601.07892

Happy to announce that Hermes Agent's repo just surpassed Anthropic's Claude Code repo

@nathanjay Optimist spotted! 😆

@nomaditsu oh shit I forgot to cancel my Hugging Face sub. Another month of creativity :'(

POV: You forgot to cancel that AI subscription 💸

Notion is now the buggiest app on my phone! Someone give them Mythos access so they can fix this slop 🥲

A Chinese company facing chip restrictions can train this But xAI can’t even get SOTA With a million H100 equivalents

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n