A guy who mentored me in marketing said: “NOBODY wants to learn to trade, they just wanna get rich”
METAWORLD
Joined February 2023
- Tweets2.6K
- Following1.1K
- Followers116
- Likes2.8K
T2JON retweeted
A note on liquidation data, because most people don't know this.
When you see a liquidation total on any dashboard, you are mostly looking at samples and models, because most exchanges don't publish the real feed:
@binance : at most one liquidation per market per second.
@okx : their own documentation says the feed "doesn't represent the total number of liquidations."
@MEXC , @kucoincom : no public liquidation feed at all.
One major CEX does it right. Bybit's allLiquidation stream publishes every liquidation, across every contract, in 500 ms batches. That's the full ledger. Respect to @Bybit_Official for leading here.
On-chain perps already live at that standard - on Hyperliquid every liquidation, size and price is public by design.
Liquidations are the single most consequential event on a derivatives exchange. They move price, they move the whole market, and they happen to your account. There is no good reason a venue that liquidates its customers can't tell the market how much it liquidated.
@binance @okx and everyone else: publish the complete feed. Transparency here is not a feature request, it's the minimum.
We build liquidate.fun on whatever the exchanges give us. Give us the truth and we'll show it, instead of a predictive model.
T2JON retweeted
I don't think you understand how truly fucked we are...
Imagine 2008 but 10x the leverage, a housing bubble, a commercial real estate bubble, a private credit bubble and a stock market bubble.
All at the same time...
We are in 1929.
T2JON retweeted
I've made over $5M from trading.
You’d think my trading breakthrough came from a new strategy or mentor, but it didn't.
It came from studying the Bible.
Today, I’m sharing the 7 Bible verses that helped me become a millionaire trader:
1) Joshua 1:8
T2JON retweeted
my friend quit his $95k/year tech job to trade full-time
everyone told him he was crazy
6 months later he was broke
moved back in with his parents
everyone said "told you so"
12 months later he was making $18k/month
24 months later he was making $40k/month
now he's at $70k+/month and just bought a house cash
here's what nobody saw during those first 6 months:
he was trading scared because he NEEDED it to work
the pressure made him overtrade
overtrading made him lose
losing made him more scared
more fear = worse decisions
cycle repeated until broke
what changed:
got a part-time job (removed financial pressure)
traded like he didn't need the money (because he didn't)
made money because he wasn't desperate
the lesson:
don't quit your job to trade
trade until trading REPLACES your job income
then quit
the desperation tax is real
and it costs more than any mentor or course ever will
by my estimates... if all this chatter is correc then... bombs away somewehre in the middle east approximatley 90 mintues from now...
B1 bombers left UK... verify yourself... NFA
T2JON retweeted
20 TIPS FOR USING JEV FROM 0 TO PRO
TypeSafe just shipped the first model built for machines, not for people.
Here are my top 20 tips on how to actually use Jev:
1. stop treating it like an LLM. Jev doesn't write, it decides. state in, typed decision out.
2. three primitives: Choice picks from a list, Score places it on a rubric, Noul returns a 0-1 probability.
3. the architecture: LLM generates, Jev decides, code controls, humans catch the uncertain cases.
4. skip personas and preambles. state + one atomic question + exact criteria.
5. descriptive criteria beat labels. "technical = broken behavior or integration failure" beats "pick the right team".
6. one question, one judgment. "valuable, urgent and likely to buy?" is three questions you combine in code.
7. never ask it to explain itself. decision, probability, confidence. that's the contract.
8. keep state clean: the object, the context to read it, the facts that change the call. nothing else.
9. 64k limit, but accuracy shifts as state grows. the smaller useful state is the upgrade.
10. batch your questions. one call can judge 13 dimensions in parallel and barely move latency.
11. ask everything you might need, even what you'll throw away. output tokens are free.
12. gate on confidence, not the answer. act above 0.85, escalate 0.55-0.85, human below 0.55.
13. tune those thresholds on your own data. numbers from a post are a starting point, not a config.
14. every uncertain answer needs a route. low confidence treated as normal is how bad decisions ship.
15. never let it invent options. build the candidate list in code, then let it pick.
16. keep arithmetic and hard rules in code. Jev judges meaning, your program does the math.
17. pin the version. jev-latest to track stable, jev-1.13.0 once your thresholds are tuned.
18. log model ID, probabilities, confidence, route, outcome. review false positives, retune.
19. put it in the loop, not next to it: route before the call, gate the tool, judge the output.
20. the five money workflows: universal verifier, support triage, lead scoring, model routing, giant dataset jobs.
setup: waitlist at typesafe .ai, then read how to build the fastest ai agents systems with Jev in article below.
T2JON retweeted
here's how JEV works, simplified
I've been experimenting with it for the last hour, and it's EXTREMELY good at making decisions with the right references and context
you give it the information, your questions, and the type of answer each question needs:
> a choice from options you provide
> a score on a scale you define
> a probability that something is true
the models we're used to often give us long written answers, with explanations and reasoning
jev returns structured answers your app can use directly, instead of generating those explanations
information + your questions + allowed answers → answers your app can use
you define what happens next, based on those answers
that could mean sending information to the right place, checking an AI agent's work, or flagging something for human review
because jev doesn't generate prose, it doesn't invent facts or sources inside a written explanation (hallucinations)
clear questions and useful context matter, including references that explain what it should check
I'm seeing so many cool use cases across X, and I can see people adding this to all kinds of existing apps
if you haven't started building with it yet, try it on one decision your app already makes
the new jev model is insane..
it can check your AI's work and make decisions inside software for $0.042 per million input tokens, with free output
here are the first things you should use jev for:
1. second brain
2. content workflow
3. post analysis
4. SEO article review
typesafe reports up to 193.6× faster results and 444.6× lower costs than the LLMs in its workflow tests
you give jev information and specific questions. it returns choices, scores or probabilities that your software uses to decide what happens next
1. second brain
when a document, message or meeting note enters your second brain, give jev the content and your categories
identify what it is, classify the topic and check for duplicates against existing notes
your software checks required fields, saves the content with its source and verifies that it was saved correctly
works well with the karpathy LLM wiki framework
2. content workflow
give jev your draft, and then reference your anti slop rules and voice DNA file (which defines how you write)
it will check for generic phrasing, repeated points and differences from your voice. use previous content and its results to estimate performance potential
then send results to the writing agent for revision, compare the performance estimates with results after publishing
3. post analysis
jev can compare a draft with previous posts and their results to estimate how well it could perform with your audience
evaluate the hook, topic and format against defined criterias. and compare those scores with the performance after it goes live
4. SEO article review
give jev your article / page draft, a target keyword and the articles currently ranking for that keyword (in the top 10 SERP)
compare how well they answer the query, cover the topic and provide useful information. use that comparison to estimate your article's ranking potential
then your LLMs can revise weak sections before publishing, and compare the estimate with actual rankings
so many more usecases, we will see many new upgrades to previous concepts and workflows we´ve read about now
