polymathic_man
4.9K posts
polymathic_man
@polymathic_man
Raising unbreakable kids. Guiding men to strength & authentic love. Crypto fuels wealth & freedom. AI for truth.
Se unió Ocak 2020
229 Siguiendo260 Seguidores
Introducing Hermes Agent v 0.13.0
- Multi-Agent orchestration through the Kanban system
- Enforced goal completion with /goal
- Big optimizations for disk usage
- Much more extensibility, custom LLM Providers, custom gateway channels, and much more
Nous Research@NousResearch
Hermes Agent v0.13.0 - “The Tenacity Release”
English
A little Cashtag upgrade for the traders on X:
Charts and prices embedded directly into posts
$TSLA
English
Many Gen Z on social media are saying they are "excited" for another lockdown if it happens due to hantavirus
According to them, they want to experience the Covid-era vibes again
English
@JonnyRoot_ I thought they said the best version is Emily Wilson's
English
Christopher Nolan’s The Odyssey might actually be liberal, woke trash…
- The script is reportedly based on Emily Wilson’s 2017 version of The Odyssey, which modernizes (& dumbs down) the language, puts more focus on female characters & power dynamics, rather than masculinity, & makes Odysseus less heroic and more morally “complicated”
- Ellen Page (Elliot) is rumored to play the ghost of Achilles. From Brad Pitt to a tranny… What a downgrade.
- Black actress Lupita Nyong'o is rumored to play Helen of Troy. Another race swapped character, who clearly does not have a “face that launched a thousand ships"
I was excited about this movie but this could turn out to be a self-inflicted, epic disaster.
English
JUST IN: Scientists working to create hantavirus vaccine, per BBC.
English
@StefanMolyneux Women you mean, try putting your philosophy on women let's see
English
I hope you can see why I put my trust in philosophy rather than religion
David@David_wthebeard
“Jesus isn’t the way the truth or the life exclusively. There are many ways to inherit eternal life.” –Satan himself
English
@MarioNawfal The weekend is approaching, and the market is closed. Time to fight!
English
🚨🇮🇷🇺🇸 THE CEASEFIRE IS OVER
IRIB, Iran's official state broadcaster, confirms Iran has fired missiles at US naval units in the Strait of Hormuz.
This is not a claim. This is the Islamic Republic announcing it.
Mario Nawfal@MarioNawfal
🚨🇮🇷 BREAKING Multiple missiles fired from southern Iran into the Strait. Per local Iranian reports.
English
JUST IN: Tom Lee says Ethereum's fair value is $22,000
English
🆓 Not going to lie, based on my benchmarking Hy3 is a good model! They have also been very generous with free tokens. Yes, those free input tokens make their way back to the vendor so just be aware.
Tencent Hy@TencentHunyuan
Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week. #1 in overall usage, tool calls, and coding. 15.4% market share across all providers.🏆 Top apps running Hy3 preview: Hermes Agent, Claude Code, Kilo Code, OpenClaw, Cline.@NousResearch @claudeai @kilocodehq @openclaw @cline Huge thanks to every developer building with it. 🙏 Try it on OpenRouter: openrouter.ai/tencent/hy3-pr…
English
-Get a Tesla
-Change air filter
-Replace/rotate tires
That's it.
theficouple@theficouple
How to help your car last 300k miles: -Get a Toyota -Use synthetic oil -Change air filter -Use top tier fuel -Buy a Toyota What would you add?
English
@googledevs I'll wait for qwen3.6 27b -it-assistant → The tiny drafter model specifically built for that IT version.
English
Gemma 4: Now up to 3x Faster. ⚡
Same quality, way more speed. Our new MTP drafters allow Gemma 4 to predict multiple tokens at once, effectively tripling your output speed without compromising intelligence.
GIF
English
@TeksEdge @OpenRouter All expiring. Minimax 2.5 not usable. Offline all the time
English
Have you seen how many free models are available on @OpenRouter? It’s at least 30 by my recent count. There’s even an API that calls a free model every time @ $0/1M token.
English
carnice-v2 is up now on my rog 5090 mobile 24gb tier, llama-server holding 21gb at 262k context, hermes agent on the other pane, nvtop watching the line go up. hell yeah tonight is gonna be great.
if you are running with me on 24gb vram, here is the exact stack:
./llama-server -m carnice-v2-27b-Q4_K_M.gguf -ngl 99 -c 262144 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 --port 8080 --host 0.0.0.0
3090, 4090, 5090 mobile, w7900, anything 24gb, copy the flags and share what you got. if you have not run carnice on your card yet anon, what is stopping you?
Sudo su@sudoingX
a question keeps hitting my mind. does same base SFT for harness beat vanilla qwen 3.6-27b on hermes agent agentic loops? to find out i loaded carnice-v2 by kaios, qwen 3.6-27b tuned specifically on hermes agent traces. trinity 3-stage merged bf16 SFT. i have been benchmarking vanilla 3.6 on agentic tasks for weeks so i would catch any meaningful improvement on a head to head. been wanting to run this exact lineup. carnice on the same hardware, same context, same flags i run vanilla on. let's see how it performs against the base. hardware: rog scar 5090 mobile, 24gb vram tier. every flag i use reflects directly to your 3090 desktop 24gb territory, so if you are running a 3090 you can copy the same setup and follow along. results coming next anon.
English
@RoundtableSpace $doge The golden cross was detected today (May 4, 2026)! Can somebody confirm this?
English
