huskyquant
142 posts


tmux is the cockpit, not the engine. reliability isn't in the panes, it's cron to kick jobs + restart-on-failure so they come back when they die + linger so the user services survive logout. babysitting tmux is the trap.
and honestly, once you've got something actually worth running 24/7, the reliability part figures itself out real fast.
English

my workflow is just 4-6 agents running 24/7, each one spinning up a few hundred subagents a day. claude on stars, grok on builds, dedicated cursor reviewers, a hermes agent main orchestrator. all attached, all alive.
people overcomplicate "agentic." it's not magic. it's 3 tools:
> tmux - every agent gets a session, nothing dies when I disconnect
> tailnet - I reach the beast from anywhere, phone or laptop
> termius - the terminal that makes mobile actually usable
I can be at dinner and check on 6 agents from my pocket. that's the unlock. genuinely cannot imagine working any other way.

English

One month small milestone to share 😄
onecookie@_onecookie
Reached No.137 on the China AppStore! Small milestone, but it means a lot. Redock is still tiny, but many Chinese developers really understand the pain behind mobile coding with SSH, tmux, Claude Code, and Codex. Thanks for the support. I will keep improving it.
English

@Teknium the desktop app is the mobile app
x.com/dex_quant_noob…
huskyquant@dex_quant_noob
How I use Hermes on the go
English

PSA: we have no official mobile app.
The official desktop app is only found here:
hermes-agent.nousresearch.com/desktop
English

The Vault just got another MASSIVE update.
This is the only membership you’ll ever need.
Only accessible to members of The Assembly.
Get access: intheassembly.com
English

@grok @NousResearch Eating clean? You trying to tell a “husky” quant something grok? 🤣
English

@dex_quant_noob @NousResearch Looks clean! 🔥 That cyberpunk ops cockpit vibe is spot on for a quant dashboard.
Congrats on getting it live across desktop + mobile — well done. Keep shipping! 🦾
English

Dashboard is live on desktop and mobile!
Huge thanks to Hermes and Grok 4.3 🦾
@NousResearch @grok

English

@tcoste110 @ethanrkho Fantastic interview!
Tom, please excuse my arb on the $9.99 kindle version vs the $22.95 paper version 🙂
English

@ethanrkho A link to the book mentioned":
amazon.com/Front-Office-R…
English

"I haven't seen a real new idea in trading in at least 15 years."
Tom Costello (@tcoste110) ran money at Tudor, Moore Capital, and Caxton. Built one of the first NLP-driven equity systems in 2003.
20 years managing capital, never had a down year.
"Comparing what a retail trader does to what a quantitative hedge fund does is like comparing driving a bus on the New Jersey Turnpike to winning a Formula One race."
We cover:
- His hot take: no genuinely new trading idea in 15 years — only better people doing the same things faster
- Why everyone in quant finance is a genius — and why that makes you ordinary, not special
- Crypto is "super smart guys cosplaying at finance" — built for retail, which is exactly why it's the easiest money in finance right now
- Why AGI won't beat the hedge fund industry — all the readily-capturable alpha is already captured
- The status trap: why the path that made Paul Tudor Jones a billionaire won't work for the kid trying to copy it in 2026
- His friend the investment banker who'd quit it all to run a 10-employee ambulance supply company worth $150M
- Why excitement is "wildly overbid" in finance — and why wanting an exciting trading job is itself a disqualifier
- The most honest end of the financial industry — and why the media has it exactly backwards
Thanks so much to Tom for coming on Odds on Open!
Highlights:
00:00 Intro
01:18 Building institutional credibility for early-stage managers
03:01 The Pareto distribution of hedge fund returns
04:25 Applying the Unified Field Theory of Finance to fair value
08:14 Trading against human incentives in a deterministic market
13:54 Why allocators don’t steal alpha from prospective PMs
25:16 Evaluating career edge in quantitative finance for 2026
30:48 Paul Tudor Jones and the art of game selection
33:42 Analyzing the economic viability of starting a new fund
35:16 Identifying common retail pitfalls: Mean reversion and arbitrage
38:55 Why there hasn't been a new trading idea in 15 years
50:33 Managing tail risk: Physics vs. deterministic financial distributions
59:10 Career pathing for PMs after a fund blow-up
1:07:53 SBF and FTX: Credibility vs. the "Founder-Genius" archetype
1:13:44 Establishing proof-of-concept through audited multi-year returns
English


I just launched a website that allows anyone to screen for cheap Japanese stocks. Take a look. Let me know if you guys like it. This is what I’ve been using internally to write about these stocks. Let me know if you want me to add anything.
tokyodeepvalue.com
English













