Head Coach @ Precision Athletics Fencing 🤺 | Coaching national medalists - Foil 🏅 | Camp Director, Fencer's Paradise 2026 🌺 | AI Tinkerer 💻 | Climber 🧗
Los Angeles, CA
Joined October 2009
- Tweets2.5K
- Following264
- Followers259
- Likes5.5K
25 years of coaching fencing taught me that the hardest moment is the one where you have to commit with no backup plan.
Turns out bouldering works the same way. Feet off, one shot at the hold, all in.
V6. Sent.
#bouldering #climbing #GymClimbing #crosstraining #Athlete
This game, and especially this level - made me understand how one can never give up... Just try again, eventually you will succeed!
A little roof climbing session! 🧗♂️💪
Some fun moves, tricky footwork, and a good test of grip strength. Always satisfying to finish a challenging route!
#Bouldering #RockClimbing #ClimbingLife #GymClimbing #Athlete
Takamatsu 🇯🇵🤺
Proud coach moment. My student Kaylin Hsu fenced her first-ever Senior World Cup and delivered: made day 2 and finished top 64, earning both international and domestic points to boost her ranking. First senior event. Top 64. Huge. 👏 @PrecisionAFC
It was also a pleasure to be in Bryce Louie's corner and help him fight his way into day 2 as well. 💪
Grateful for these athletes and every hour of work that leads to days like these.
#Fencing #Travel #CoachLife #TeamUSA #PrecisionAFC
Sent the @fencing_fie an updated photo. They laminated the old one...
RIP mustache. Gone from my face, never from the FIE database. 🥸🤺
#Fencing #CoachLife #Esgrima #Escrime #Scherma @usafencing @precisionfencing
Wow, this will be my main model... At least until we see what Qwen releases this month!
Run the most cyber capable open model at home 🔥
GLM 5.3 EXL3 for 3x DGX Sparks with TensorFold on your 3x DGX Sparks is now LIVE
- Full GLM (not flash)
- Total 5M KV cache
- Yes, ~5,230,000 tokens
- 500k context
- Decode ~31 t/s in prose, 41 t/s in code
- 450k needle passed
There is a catch:
Currently, only 1 stream is supported with 500k context. However, you can run multiple conversation, each on its stream, and the KV cache pools holds them all.
I'm working with @ashxhart to fix it next, so we could actually run concurrent streams with 500k context each.
Excellent quality for coding! Working on a 4x DGX Spark version next. Expect further improvements!
Get it here:
mia-ai.net/models/GLM-5.3-EX…
Yo, @MiaAI_lab — any chance you’d consider building a 3× DGX Spark recipe for the full GLM-5.3?
Ideally something heavily optimized for fast inference/TPS while keeping as much quality as possible. I’m running 3 Sparks now and would love a turnkey TP3 setup similar to your GLM-5.3 Flash work.
Unless, of course, you think there’s a newer/better open model right around the corner that would be more worth targeting 👀
I just bought one of the LAST GB10 rigs (HP ZGX Nano G1n) from ProAdvantage! I will soon have 3 sparks at home, I'm excited to load even better models released over the coming months!
V6 send ✅
This one had a couple moves that felt way harder than they looked — especially that tiny hold in the middle.
Getting to it was one thing.
Having to MATCH on it was another. 😅
Held it together through the crux and finished the send with the match up top.
Definitely one of those climbs where the video does not fully communicate how bad the hold feels.
🧗♂️ V6
✅ Send
#climbing #bouldering #v6 #rockclimbing #climber #boulder #climbingtraining #indoorclimbing
Mia has the best local model recipes, she fine tunes each model to work with different quantities of DGX Sparks. Check out her site, and maybe find your way to the donation part of her site - she deserves every penny!
Come check out my website.
It includes a list of my latest & greatest recipes.
The "Install Model" button gives you a ready-to-use prompt for Claude, Codex, or others. It adapts the recipe to your setup, starts the server and tests it.
mia-ai.net/models
It seems as if "Space Bunny" is likely the new MiniMax model. From everyone's testing, where does it rank? I fully understand it is NOT near Opus 5.5... but how does it rank with GLM 5.3 flash, DeepSeek 4.1 flash, or other Chinese models? @bijanbowen @MiaAI_lab (I trust you both)
I may be able to aquire an R1 (device made by @rabbit_hmi). Anyone have experience with the OS3? Is it useful for your agentic work?
Forrest MacDougall retweeted
Welcome back to Hermes Agent, Claude
New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again!
Check it out and install it here: hermes-agent.nousresearch.co…
