Pinned Tweet
I'm bad at chess. So my AI agent built me a coach.
Play on Duolingo → Stockfish grades every move overnight → blunders get drawn → a training plan is waiting when I wake up.
Zero clicks. One Hermes Agent skill.
What would you want coached? 👇
nitter.gq/PaulTisl/status/211542…
@Teknium @NousResearch Today’s Hermes Agent Usage: Chess Coach!
1) Pull all games from Duolingo and save in standard notation format to Obsidian Wiki
3
3
115
My son would love a Hogwarts GPU :)
We're giving away a Hogwarts Legacy custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with DLSS 5 🪄
To enter:
🟢 Share this post
🟢 Comment #RTXON
Terms and Conditions: nvidia.com/en-us/geforce/con…
3
I want an AI that sorts my email on my own Mac. Anyone on underdog have an invite? @underdogai nitter.gq/0xSigil/status/2117395…
I bought every billboard in the SF bay area cuz I’m pissed BIG AI IS STEALING OUR DATA
Cloud-based AI & servers are getting hacked rn. Go LOCAL
No data centers, no servers, no Linux vps
1
34
Like most of us, I didn’t have the pleasure of knowing you personally. I only caught glimpses of you through your incredible performances. The world is a little colder and the sun a little dimmer today. Prayers for you, your family, and your loved ones. 🙏
In lieu of flowers, memorial contributions may be made to:
Johns Hopkins Alzheimer’s Disease Research Center Fund
alzresearch.org/giving/
Alzheimer’s Foundation of America Caregiver Resources
alzfdn.org/donate/
Photo Credit: Tommy Garcia
10
5) Hermes offers to create reusable skill **WIN**
6) I tell it to create a nightly job to ingest new games and run them through the reusable skill. Also a weekly progress report as well.
All of this from a minimal set of prompts.
Thank you @Teknium @NousResearch and all the countless people on X and in the AI labs for creating the tools and models to make tools like #Hermes to let dreams become reality.
24
3) Repeat for all 70 games in Duolingo. Analyze all 70 games to identify tendencies and weaknesses.
1
27
Paul Tisl retweeted
JUST ANNOUNCED 🚨 Your life is about to get a little funkier! Don’t miss Tower of Power & @wartheband in the @mysticlake showroom on 2/26. Tickets go on sale 10am 10/30. Learn more: towerofpower.com/tour/
#MysticLake #TowerofPower #WAR #MysticShowroom
Paul Tisl retweeted
Try Underdog: free, capable, private AI running locally on your device
New build and Saluki 27B are out. Under 8GB, beats Qwen 3.8 27B at tool calling
Like, repost, and comment one task you wouldn’t give a cloud agent to get an invite🦴
Today we're releasing Underdog Saluki 27B
Based on Qwen 3.8 27B, Saluki is almost 7x smaller than its full-precision counterpart while it keeps 96% of its benchmark performance and beats Qwen at tool calling
It's the best model <8GB that runs in Underdog
Saluki is available today under Apache 2.0. Try today in Underdog underdog.ai/saluki
Paul Tisl retweeted
Six months ago I had a hunch.
Local AI won't become the norm until it feels instant. Running a model on your own machine should feel like magic, not like tapping your fingers waiting for a reply.
The response to TensorFold since has blown me away. Thank you to everyone testing it, sending PRs and sharing feedback.
There's a lot more speed to unlock. Right now most of my time goes on reviewing and landing PRs. That matters, and every fix makes TensorFold better, but the biggest gains are in deep performance work I can't get to quickly.
If you want to see what TensorFold can really do, backing would let me work on it full time, with the hardware to test faster and dig into performance, and bring it to everyone in local AI.
All in the open under Apache-2.0.
We have been made aware that TF is being run in real production environments, so we could potentially look into support packages.
To back the project, sponsor hardware or talk about support, my DMs are open.
Even just sharing this post helps. 🫶🏼
Paul Tisl retweeted
Yeah, don’t give Meta’s Muse app access to your Mac 9to5mac.com/2026/09/28/yeah-… by @benlovejoy
Running Local.ai brings privacy back into your control.
local.ai/trexx/invite
Paul Tisl retweeted
Everyone wants to learn Machine Learning
Almost nobody gets past the tutorials
They watch hours of videos
Save hundreds of resources
And still don't know how to actually build with ML
That's why I'm sharing the Machine Learning with Python Cookbook by O'Reilly
169 pages of practical ML with Python from preprocessing all the way to deep learning
Less theory
More building
If you're learning ML in 2026 you'll want this saved
Giving it to the first 4500 people only
Follow me so I can DM you
Like + RT
Comment "ML"
Once the limit is reached I'll stop sending it
Paul Tisl retweeted
I created a playbook to help you learn AI engineering.
It'll give you:
• Core concepts behind AI systems.
• Condensed notes to understand full-stack AI engineering.
• Must know techniques to build, deploy & scale AI apps.
(24 HOURS ONLY!!!)
1 Follow @systemdesignone [MUST]
2 Like & Retweet to get DM
3 Reply "Playbook"
Then I'll DM you the details.
Clear walkthrough of LoRA, LoRA+, QLoRA, VeRA & DoRA — how to fine-tune big models without touching every weight. Handy if you're building on local LLMs.
youtube.com/watch?v=U80tjcTh…
1
45