Charlie

Building with AI, Nosistech

[Nous Research @NousResearch]

Introducing the Hermes Agent Profile Builder

You can now build a complete profile in the dashboard with full control over identity/name/description, model/provider, built-in + optional skills, skills-hub installs, and MCP servers in one easy flow

[Charlie @arparvar]

@leopardracer Great setup. I have a 5070 TI 12GB VRAM with Gemma 4 and Hermes Desktop @NousResearch
https://t.co/jwssiwy7Yo

[Charlie @arparvar]

@googlegemma If you are trying to run Hermes Agent with Gemma 4 and getting a context window error (even after setting it to 64k+), it is likely due to parallel_slots in llama.cpp.

https://t.co/I5wvQrVFqR

[Charlie @arparvar]

@JMasterFarm @JulianGoldieSEO Read my post, it has a fix to the 32k context window. Hopefully it applies to your case. I am running Gemma 4 on a 5070 TI 12 GB VRAM over 100 t/s https://t.co/jwssiwy7Yo

[Charlie @arparvar]

@tobiaswup this looks great. I got really great results, use a little bit more VRAM because of optimizations. https://t.co/jwssiwy7Yo

[Charlie @arparvar]

@analogalok https://t.co/jwssiwy7Yo tested this and got great results.

[Charlie @arparvar]

@madsf88 La Colombe Coffee Workshop https://t.co/gCxPUZoiCQ

[Charlie @arparvar]

@andrewbrown 🤝 Looking forward. When will the link to sign up be https://t.co/sQ0SN2Boxi

[Charlie @arparvar]

@niyetsel .

[love @nuketowngodzila]

@BowTiedBull supports not that it needs to but does,on your museum/ art viewing practice!

[Charlie @arparvar]

@goodhunt @arcee_ai Congratulations! Recently tried codewhale, love it.

[Xiaomi MiMo @XiaomiMiMo]

🚀 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.

[DeepSeek @deepseek_ai]

We are making our discount permanent! 🎉

Enjoy building with DeepSeek-V4-Pro and bring your innovative ideas to life! 🚀

[Charlie @arparvar]

@andrewbrown HBD andrew. 🤝 🎉

[Charlie @arparvar]

@elder_plinius Hope you are well and recover soon 🙏

[Charlie @arparvar]

@andrewbrown 3. BYOAA

[Charlie @arparvar]

@fromzerotomill stack

[Charlie @arparvar]

@cyrilXBT CLAUDE

[CooperBaggs 💰🍞 @edgaralandough]

I saw a girl say that when she feels stuck, she imagines she's 85 years old and gets one chance to come back to her younger self for one day, suddenly, everything feels like magic again, the walk, the music, the sunlight, live everyday like that.

wow. im doing this DAILY now.

[Charlie @arparvar]

@maarcoofdezz @aiscwork I need Claude to learn more and faster about AI