Tweet ghim
Encontrar la verdad, sin importar quién la tenga; desenmascarar la falsedad, sin importar quién la difunda.
Español
Juan de Villeros
1.9K posts
Juan de Villeros
@jmdevilleros
Retired IT pro (20+ yrs). C, Kotlin, Dart & Python coder. AI enthusiast. Linux advocate. Gamer at heart.
Tham gia Kasım 2009
456 Đang theo dõi115 Người theo dõi
@jmdevilleros @opencode For the Mimo v2.5 Pro do you normally use low, medium, or high?
English
English
@opencode At Go, which is the best model for Plan and which is the best for Build mode?
English
I think it's a form of the classic dichotomy between top-down and bottom-up approaches.
There's use cases for both. I tend to use top-down in my software, starting with a working prototype. Reminiscence of the days I was writing C programs making sure they compiled and ran after every change. Progressive rendering.
English
finally found the right metaphor for this shift in how i use opencode.
i used to treat it like 3D printing, where you build the thing layer by layer and commit to each piece as you go
now it feels more like progressive rendering, you start with a blurry version of the whole thing, then keep making full passes over it, and each pass sharpens the entire shape
doing this with gpt 5.5 and voice prompting is the first time things feel like they're clicking
English
Thought experiment:
Imagine we built the world's most advanced AI. Imagine it is not just very smart: It is smarter than all humankind combined, by an order of magnitude. It can cure all diseases. It can figure incredible investment opportunities. It can break almost any code, reverse engineer anything, be hyper persuasive, invent anything and solve any problem, etc.
But there's a catch: Each prompt costs $100,000,000.00 (a.k.a a ton of actual resources) to run.
Now:
1-Who would have access to it?
2-Who gets to decide 1?
3-What would these people use it for, first and foremost?
4-How would governments feel about that?
5-How would that affect most people on the planet?
English
I have still yet to meet someone actually using hermes.
Whenever I mention it, i just get bots in my replies.
Openclaw 4 lyf
Nous Research@NousResearch
Hermes Agent is now #1 on the Global @OpenRouter token rankings. While our journey together has just begun, we'd like to take this opportunity to thank our contributors, supporters, and users for all they have done to get us this far.
English
@jun_song @Kimi_Moonshot @Zai_org @deepseek_ai @Alibaba_Qwen @ErnieforDevs @XiaomiMiMo Xiaomi without a doubt.
English
If you had chance to work with one of these open source AI companies, which one would you choose?
-@Kimi_Moonshot
-@Zai_org
-@deepseek_ai
-@Alibaba_Qwen
-@ErnieforDevs
-@XiaomiMiMo
English
haven't met a single person that uses opencode
dax@thdxr
i've had a major shift in how much i use opencode in the past month it's tricky to articulate but seeing someone use it 10x more than made made something click what's weird is there's no fancy workflows or skills or anything, we're still just talking to the vanilla agent
English
@llmdevguy I've had mixed results with MiniMax 2.7, as it tends to botch long directory names. It's a problem when it comes to CI/CD operations.
English
🇨🇳After testing Chinese models over the last few weeks, my coding ranking currently looks like this:
1. Kimi K2.6
2. GLM-5.1
3. MiMo V2.5 Pro
4. MiniMax 2.7
5. DeepSeek V4 Pro
👉But each of them has its own superpowers.
Frontend/Design: K2.6
Backend: K2.6 / GLM-5.1
Code review: MiMo
All-rounder: M2.7
Reasoning: DeepSeek
Now I'm waiting for MiniMax 3.0, which I hope will take the number 1 spot!
English
Juan de Villeros đã retweet
The cost of inaction is usually much higher than the cost of making a wrong choice.
English
Usar MacOS está bien.
Usar Linux está bien.
Usar Windows está bien.
Cualquier SO está bien mientras te haga ir más rápido en tu workflow de trabajo y vaya con tus necesidades.
Nicolás Schürmann@_nasch_
Me da pena las personas que siguen usando Windows porque están obligadas a usarlo. Ojalá pudiesen usar MacOS o Linux y ver que la vida puede ser hermosa.
Español
I’m coming to the conclusion that the biggest challenge for Enterprise AI, and AI in general , as of now, is that it’s still impossible to make sure that everyone gets the same answer to the same question, every time.
Which is a great response to the doomers. AI doesn’t know the consequences of its output.
Judgement and the ability to challenge AI output is becoming increasingly necessary, and valuable.
Which makes domain knowledge more valuable by the second.
Am I wrong ?
English
Cuál es su modelo chino favorito? Para que lo probemos hoy desde cero echando código. En principio tenemos en el radar GLM-5.1 de Z.ai, Kimi K2.6 de Moonshot AI, Qwen3.6 Plus, MiniMax M2.7 y DeepSeek V4 Pro. Vamos a ver qué es lo que es!
Freddy Montes@fmontes
Como Claude no nos paga (@anibal lo dice en cada episodio), hoy vamos a probar EN VIVO modelos chinos. 6 PM 🇲🇽 🇨🇷 7 PM 🇨🇴 🇵🇪 8 PM 🇻🇪 🇨🇱, 9 PM 🇦🇷 LINK ABAJO DALE RT PLISSSSS!!!
Español
@mjovanovictech I exchanged Sonnet 4.6 for MiMo v2.5 pro and never looked back.
English
I burned through ~33% of my credits in 2 days... Yeah, this isn't gonna be sustainable.
That or the cost of using AI for coding will rise significantly.
Currently testing out some "cheaper" models to see how they compare versus Opus.
Milan Jovanović@mjovanovictech
Claude Opus 4.7 now has a 15x multiple in GitHub Copilot
English
Technical debt accrues fast. Quality is evident in application architecture made by seniors. For coding, AI agents are typewriting helpers, they shouldn't replace creativity.
Suhas@zuess05
I am actually curious. If junior devs are using Claude to write code at a senior level... And senior devs are using Claude to write code at a senior level... What exactly is the difference between the two roles right now, other than a $100k gap in salary?
English
I'm on Xiaomi MiMo Open Platform — running Xiaomi's flagship MiMo V2.5 and the rest of the lineup. Sign up with my code and you'll instantly get $2 in API credits. Code: 4E2TH7 · platform.xiaomimimo.com/?ref=4E2TH7 (After signup, enter the code at the bottom-left of the console. Credits valid 40 days.)
English
@_LuoFuli Wonderful run, absolutely marvelous model. My new favourite! Thank you very much to the MiMo team!
English
Just dropped two open-source models: MiMo-V2.5-Pro (Code Agent, 1T total) and MiMo-V2.5 (Multimodal Agent, 310B total).
Oh and one more thing — we're giving devs & creators 100T tokens on us. Go build something cool 🛠️
🎁 100T Free Token Grant for Builders 100t.xiaomimimo.com
Xiaomi MiMo@XiaomiMiMo
Xiaomi MiMo-V2.5 is now officially open-sourced！ MIT License, supporting commercial deployment, continued training, and fine-tuning - no additional authorization required. Two models, both supporting a 1M-token context window : • MiMo-V2.5-Pro: built for complex agent and coding tasks, ranking No.1 among open-source models on GDPVal-AA and ClawEval • MiMo-V2.5: a native omni-modal model with strong agent capabilities A model's value isn't measured by rankings alone — it's measured by the problems it solves. Let's build with MiMo now! 🤗 Weights: huggingface.co/collections/Xi… 📄 Blog: #blog" target="_blank" rel="nofollow noopener">mimo.xiaomi.com/index#blog
English
This is her vaginal microbiome report. 100/100 score.
Top 1% of all vaginas.
Her sample is dominated by the single most protective bacterial species a vagina can host (Lactobacillus crispatus).
Only about 25-30% of reproductive age women globally are L. crispatus-dominant, and “dominant” usually means above 50%. Kate is at 98.7%.
The lab found nothing bad to report. (no gardnerella, Candida, STIs, opportunistic pathogens, aerobic vaginitis markers, etc.)
This is linked to lower risk of BV, UTIs, yeast infections, HPV persistence, HSV-2 and HIV acquisition, preterm birth, and improved IVF outcomes.
A vaginal microbiome is downstream of everything: sleep, glucose control, stress, gut health, sexual health, immune function, what you eat, and what you put in it.
English