Irell Zane

@mattpocockuk I see you've created batch-grill-me that solves this issue. Amazing!!

@mattpocockuk 100% agree, much more efficient. However, I've felt that one thing I lose are the questions that would potentially arise from the answers to previous questions when we were doing them sequentially.

I just modified /grill-me locally to ask all its questions at once... ...and I kind of loved it Just lets you dictate out a bunch of answers all at once and doesn't have the failure mode where you just say "I agree" turn after turn. Hm

@MrAhmadAwais SO TRUE. miss when it was just nerds nerding out on Twitter and Stack Overflow threads and actual engineering debates, not benchmarks and token counts.

I miss developers discussing real engineering over tokenmaxxking stats.

@DavidOndrej1 Entire Google Workspace rebranding still 100x worse

not sure how i feel about the OpenRouter rebrand...

@maxktz lol you should try this with the Chinese models with ^opus-[1-9]\d*.[1-9]\d*$

excuse me?🫪

@maxktz Verified. I tried this in pi agent and it replied gpt-5.3.

@DavidOndrej1 I was honestly skeptical for the longest time, could it really be better than the other existing harnesses? I installed it recently, it’s amazing!

install pi agent. trust me.

@CommandCodeAI 100% GPT-5.6. GLM 5.2 is amazing for open-source, yet even for value GPT-5.6 still comes up on top.

GPT-5.6 vs GLM 5.2?

@TechnoEdgeJP If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

GPT-5.5匹敵のローカル翻訳AI「Hy-MT2-30B」が無料公開。1.8B軽量版でもMicrosoft有料翻訳APIを凌駕（生成AIクローズアップ） | テクノエッジ TechnoEdge techno-edge.net/article/2026/0…

@geekbb If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

Hy-MT2 来了，1.8B 在丐版 Mac mini 上做翻译还真不错。 huggingface.co/tencent/Hy-MT2…

@YoheiZuho If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

最近登場して話題を呼んだHy-MT2をllama.cppで動かして、自宅に翻訳Webアプリを構築した。かなり精度が高くてこれを自宅に置けることにとても時代の進化を感じる。 フロントエンドはOmniPolyを、バックエンドにはOpenAI APIをLibreTranslateにラップできるプロキシを作って配置している。

@TencentAI_News If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

Open-sourcing Hy-MT2 today 🌱Three model sizes, 33 languages: 🪄1.8B: 440MB, runs on mobile chips, beats Microsoft's API 🪄7B: best-in-class among open-source models 🪄30B-A3B: state-of-the-art, outperforms models 10x its size GitHub 👉github.com/Tencent-Hunyua…

@XAMTO_AI If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

腾讯这不声不响就放了个翻译模型Hy-MT2，才1.8B的苗条身材，连丐版Mac mini都能轻松跑起来，关键效果还真有两把刷子。 别整天只盯着GPT啦，现在国内这些小模型正悄悄补位呢——本地就能跑、不用联网、还不要钱，翻译质量也完全过得去，这才是咱们普通人该真正留意的方向。 🔗 huggingface.co/tencent/Hy-MT2…

@TencentHunyuan If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

🚀 Introduce Hy-MT2: New Open-Source Multilingual Translation Model We proudly launch our new Hy-MT2 translation model and the Tencent Hy Translation mini-program! Hy-MT2 is a powerful multilingual model supporting seamless translation across 33 languages — and it's fully open-source! It's 7B and 30B-A3B models achieve state-of-the-art performance among all open-source models on various translation tasks, surpassing models with dozens of times more parameters. The lightweight 1.8B model even outperforms mainstream commercial APIs like Microsoft and so on. Powered by Tencent AngelSlim 1.25-bit extreme quantization, it needs just 440MB storage and enables effortless local inference on mainstream mobile chips — with 1.5x faster speed vs. Hy-MT1.5. Open-source AI translation just got way smarter, faster, and more accessible! 🌏 Project Page: aistudio.tencent.com/llm/zh?tabInde… Hugging Face: huggingface.co/collections/te… Modelscope: modelscope.cn/collections/Te… Github: github.com/Tencent-Hunyua…

@TencentHunyuan If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

🙏 Thank you all for the incredible love and support! Our latest Tencent Hunyuan translation models are on fire on Hugging Face: 🥰Hy-MT2-1.8B ranks #1 🥰Hy-MT2-30B-A3B ranks #4 on the open-source model trending leaderboard, with over 7K downloads already! To make it even easier for everyone, we’ve launched the Tencent Hy Translation WeChat mini-program, built on Hy-MT2. It supports voice input and offline translation, plus powerful customization of translation styles and instructions — delivering results that better match your expectations and feel far more practical. Try it out and share your feedback with us — we’d love to hear from you! Models on HF: huggingface.co/tencent/Hy-MT2… huggingface.co/tencent/Hy-MT2… GitHub: github.com/Tencent-Hunyua… #HyMT2 #TencentHunyuan #OpenSource

@TencentHunyuan If anyone wants to test the Hy-MT2 model on iOS, I built a native app for it. It runs fully local/on-device. You can check it out here: apps.apple.com/sa/app/voco-lo…

🚀 Open-source upgrade unlocked. Tencent Hy-MT2 is now under Apache License 2.0 — maximum freedom for research, commercial use, fine-tuning, and derivatives. No strings attached.😎😎😎 Proud to push model weights back to the community. Our two variants are currently sitting at #1 and #4 on the Hugging Face trending leaderboard. Clone, fork, break things, ship feedback. The iteration loop is live.🔥 Let’s keep building the frontier together. #Tencent #Hy #HyMT2 #Apache2 #HuggingFace #OpenSourceA

@neerajjj6785 Reverting, force pushing alone DOES NOT fix this. Even if it’s not in the git history they can still be accessed through the commit hashes, and no such thing as a compromised key that can be “uncomprimised”. The responses here that mention rotating keys are the right way to do it

Interviewer: You accidentally pushed sensitive data to a git public repo. How would you fix it ?

@NousResearch Do you guys never sleep?

Hermes Agent v0.16.0 - “The Surface Release” Changelog below:

@cheatyyyy @opencode The mimo price cut is insane.

@opencode wen opencode go limits update? mimo and deepseek cost much less now

Qwen3.7 Max now available in Go - text only - 1M context - smartest model in the Qwen family to date

@XiaomiMiMo This is honestly insane. We're getting near SOTA performance at a lower cost than gemini 2.5 Lite.

🚀 Better inference efficiency, lower costs, broader access. MiMo-V2.5 Series API pricing is now permanently reduced — by up to 99% compared to previous pricing. ✨ Unified pricing across all context lengths. MiMo Token Plans have also been upgraded: • 5–8× more usable tokens at the same price • Simpler and more transparent billing rules 🎁 As a thank-you to current users, all current Token Plan credits will be fully reset. 🎧 MiMo-V2.5-TTS remains free for a limited time. ⏰ Effective May 26 at 6:00 PM PDT. These improvements are powered by continued inference optimization and serving efficiency upgrades across the MiMo stack. 🛠️ We’ll also publish a detailed technical blog on the inference optimizations later — stay tuned.