Balder's Fable Picks 龙气榜 · SIGNAL DESK
AAPL305.66MSFT495.15NVDA224.98TSLA341.18AMZN263.11GOOGL345.60META590.92AMD508.56AVGO391.42MU965.40INTC102.99NFLX78.08AAPL305.66MSFT495.15NVDA224.98TSLA341.18AMZN263.11GOOGL345.60META590.92AMD508.56AVGO391.42MU965.40INTC102.99NFLX78.08

AI-native strategies · built in the open

Trading just got an
AI-native era.
Come build it with us.

Balder is an AI-native trading desk. An agent loop researches, tests and trades — reading filings, option chains and institutional flow at a scale no analyst team can match — and every position it takes is published, on entry and on exit.

Members get more than signals. You get the tools, the structure reads, the earnings radar, and the reasoning behind every call — so you learn how an edge gets found, not just what to buy. Three engines live. More every month.

Backdrop: cumulative per-trade return across 55 closed trades (07-31–08-15) — equal weight, a sum of trade returns, not a portfolio return.

55closed trades
65%profitable
+2.23%average trade
73%earnings direction
76tickers covered

Calls that worked

Balder’s Position — the four best, entry to exit

The top four closed positions from the long book. Gold marks where the book disclosed the entry, white where it announced the exit — and because both were published before the outcome was known, the full record, losers included, is one click away.

Why this is different

Anyone can run a model. Almost nobody checks the inputs.

Most market coverage is a vendor feed with a chart on top. This desk reads the primary record and fixes what the feeds get wrong — which is where the edge actually lives now that everyone has the same models.

01

We read the filings, not a feed

The Q2 flow panel is rebuilt from SEC’s raw 13F data across 1,410 managers and 4.77M holdings — then corrected for stock splits, entity migrations, CUSIP changes and filer misreporting. Every one of those makes a vendor number quietly wrong.

02

Details other people get wrong

An earnings reaction lands on a different day for a pre-market reporter than an after-close one. Measure both alike — as most sources do — and a fairly-priced option looks 4× too expensive. Ours is session-aligned.

03

Upstream of the news

Form 4 insider buys and 13D stakes are pulled straight off EDGAR twice a day, filtered to open-market purchases with the insider’s own cash. The filing is public before anyone writes it up.

04

The loop keeps compounding

The research agent runs continuously — testing ideas, killing the ones that fail, and promoting what survives. Three engines live today. The ones that reach the site are the ones that already earned their place.

Highlights

Posts that travelled

Written by Balder, not by the machine — the desk publishes the data, these are the calls and arguments around it. Numbers are the real reach on X. Balder writes mostly in Chinese; these are the originals, unedited.

Recent opinion

The read, in order

Balder’s own posts, newest first, in the language they were written in. Click any of them to open the original on X.

08-16
1.1K views
长期仓位离开了 $BRK 因为其没有继续走强的趋势,但是补充了 $LLY 用于维持仓位的多样性。
08-16
6.3K views
我们曾经说过 铜 是除 $AMD 外第二好的交易,可惜随着黄金白银的行情结束进入了长期横盘,但铜的供需关系正出现严重的紧张,可能逐渐进入爆发期。
08-16
0 views
RGTI 跟踪中 +29.11%(2026-07-28 纳入) Balder's Posit…
08-15
6.6K views
Anthropic 度过了有史以来最为强劲的第二季度,收入达115亿美元,较之第一季度的47.3亿美元飙升143.7%,更是去年同期7.87一美元的14倍,ARR达到了惊人的1200亿美元,而老对手OpenAI目前仅为400亿美元。
08-14
27K views
Jane Street 在逆势中坚决加仓🫪 那现在应该已经恢复得七七八八了。所以只要没被打爆仓都有恢复的机会。
08-14
42K views
Jane Street 在 7 月 引起Situational Awareness 大崩溃中录得 150 亿美元亏损,几乎抹去了去年大牛市中获得利润的一半。 所以就连天天割散户韭菜的,地表最强大量化机构也在今年七月折戟。 所以我们度过了毁灭性的7月 迎来了充满希望的八月。
08-14
12K views
7785差6点,🫪很快就会有一个极为强大的蝶子策略离开shadow进入实战,可能是将会带来大结果的策略。
08-14
4.3K views
【美股复盘 · 8月14日】 **大市**|美股周五反复偏软,主要指数低位靠稳收市,全日缺乏方向。标普500指数ETF( $SPY )收报776.00点,跌0.24%;纳指ETF( QQQ )收报729.70点,跌0.32%,为三大指数中跌幅最深;道指ETF( DIA )收报537.10点,跌0.15%,跌势相对受控。资金转向中小型股,罗素2000ETF( IWM
08-14
0 views
$NFLX 的期权交易结构非常异常,期权IV极低,然后OI在每个价格上都极为爆炸…
08-14
14K views
Anthropic 10月将IPO,估值超越2万亿美元,将超过 $SPCX 的IPO,其ARR目前已经到达了1000-1200亿美元。大约是 $SPCX 的4-5倍。
08-14
7.8K views
机器人给出的target和stop只是当时交易的静态参考,他有一套自己信号体系,是完全动态的。 目前来看机器人逐渐变得谨慎看多,抛售了拉子存储等动能股,买入了大盘和老登股,然后抄底了 $CSCO 和 $APP ,主题上还是看好量子 $RGTI
08-14
15K views
智谱发布新模型GLM-5.3,performance再次全面碾压各种开源模型并且在多项基准测试超越Fable和Sol。 如果Fable 6和Astra再不出来,中美之间的AI差距已经几乎归零了。

Home/Products/24/7 Board

Markets around the clock

The market closes.
The world doesn’t.

Friday 4pm the tape stops, and for 65 hours every app you own shows you a dead number. Meanwhile Tokyo trades, futures move, and by Monday’s open the gap has already happened — you just weren’t allowed to watch it.

09:30 – 16:00 ET
US cash market
consolidated tape
16:00 – 09:30 ET
Overnight
CME futures, basis-adjusted
Sat & Sun
Weekend
Hyperliquid perps
Coverage
24 / 7
Indices
SPX · NDX
Single stocks
13
Forecasts
0
Price
free

Track the market when the market is shut

This board makes no predictions. If you want a forecast for the next session, that is a separate product — the SPX probability cone →

This one forecasts nothing. It is a live board that never goes dark: cash index during US hours, CME futures overnight, and Hyperliquid perps at weekends — so there is a real price at 3am on a Sunday instead of a stale Friday close. Every number is an actual print from a named venue. Only tickers with a genuine 24/7 venue appear; nothing is invented to fill a gap.

Open the live 24/7 board → Free · no login required
  • Indices — SPX and NDX: cash in RTH, CME futures (ES/NQ minus basis) overnight, Hyperliquid US500/USTECH perps at weekends.
  • Single stocks — 13 names with a real round-the-clock venue: US consolidated print 4am–8pm ET, then builder-dex perp marks overnight, validated to track spot within about 1%.
  • No fabricated quotes — if a name has no genuine overnight venue, it is simply not on the board.
IndicesSPX · NDX
Single stocks13 with 24/7 venues
Overnight sourceCME futures
Weekend sourceHyperliquid perps
Forecast contentnone — prints only
Costfree

Home/Products/SPX Forecast

SPX forecast

Tomorrow’s probability cone

A forecast, and deliberately separate from the 24/7 board — that one reports prints, this one puts a distribution on tomorrow’s close. Six thousand Monte-Carlo paths, gamma-adjusted, anchored on the live option chain: where dealers damp or amplify moves, and the walls that tend to pin price.

SPX probability cone

LAST SESSION · 2026-08-14

7,785.76
expected move ±70.72 · positive gamma - dealers damp moves
68% band
7,753 – 7,807
95% band
7,731 – 7,829
gamma flip
7,759.61
call / put wall
7,790 / 7,775
Sessions scored
17
Inside 68% band
94%
Inside 95% band
100%

A 68% band that contains the close 94% of the time is too wide, not “94% accurate”. The honest read is that the cone is currently conservative, and tightening it is open work. We publish the number either way.

Every session on the ledger

The band published that morning, and where the index actually closed.

Session68% band95% bandClose Expected moveResult
2026-08-147,753 – 7,8077,731 – 7,8297,785.76±70.7inside
2026-08-137,770 – 7,8197,748 – 7,8417,798.99±72.4inside
2026-08-127,724 – 7,8017,703 – 7,8237,748.50±70.7inside
2026-08-117,656 – 7,8047,584 – 7,8787,728.20±74.5inside
2026-08-107,677 – 7,8037,613 – 7,8257,753.11±72.6inside
2026-08-077,682 – 7,7617,660 – 7,7847,757.64±74.0inside
2026-08-067,669 – 7,7477,646 – 7,7727,709.96±75.3inside
2026-08-057,673 – 7,7537,649 – 7,7767,723.55±75.5inside
2026-08-047,608 – 7,7527,538 – 7,8087,736.52±80.2inside
2026-08-037,499 – 7,6187,476 – 7,6417,600.50±75.5inside
2026-07-317,378 – 7,5437,298 – 7,6257,489.72±82.7inside
2026-07-307,307 – 7,4717,228 – 7,5527,437.63±82.1inside
2026-07-297,333 – 7,5017,251 – 7,5847,316.15±84.568% miss
2026-07-287,309 – 7,4797,227 – 7,5637,428.78±85.0inside
2026-07-277,375 – 7,5517,289 – 7,6397,413.18±88.5inside
2026-07-247,317 – 7,4937,231 – 7,5817,411.98±88.5inside
2026-07-237,371 – 7,5047,302 – 7,5297,408.30±78.8inside

Home/Products/Earnings Radar

Earnings Radar

What the option market charges vs what the stock does

Published every Sunday for the week ahead. For each name reporting, the board compares the implied move priced into options against the typical move that stock has actually delivered on its last nine reports. When those two disagree, that is the trade.

Earnings Radar board

This week's board

Live predictions for the coming week, published before the reports. Verdict is the ratio of implied to typical: RICH means options cost more than the stock usually moves, CHEAP means less.

SymbolReportsSessionImpliedTypical VerdictUp-rateWindow
HD08-18pre4.2%2.0%RICH 2.10×56%this week
TGT08-19pre6.9%7.6%CHEAP 0.91×22%this week
LOW08-19pre5.1%2.5%RICH 2.05×44%this week
WMT08-20pre4.9%4.8%FAIR 1.02×44%this week
BABA08-20pre7.0%6.1%FAIR 1.15×44%this week
NVDA08-26post6.7%4.3%RICH 1.53×33%next 2wk
MRVL08-27post13.5%12.9%FAIR 1.04×56%next 2wk
AVGO09-02post10.1%11.0%CHEAP 0.92×56%next 2wk
DELL09-03post16.9%12.3%RICH 1.38×44%next 2wk
Quotes as of Friday's close. Results are appended after each report prints — this board went live this week, so the outcome column starts filling from Monday.

Previous predictions, scored

On every card the conclusion sits in the top-right badge — that is the whole read, and it comes in three colours: ■ green BULLISH means the model expects up, ■ red BEARISH expects down, and ■ grey coin-flip means it has no edge and makes no call at all.

Only the red and green calls are counted below — the same threshold the card itself uses to print the badge, so the table can never disagree with the picture. The grey ones are not predictions and are excluded rather than quietly scored as free wins — a call the model declined to make cannot be right or wrong. Click any row to see the original card exactly as it was posted on X, before the report.

Directional calls
22
Direction right
73%
Move inside range
54%
No-call (skipped)
30
SymbolReportedSessionOur call ExpectedActualResult
CSCO08-12postBEARISH±7.2%-8.4%hitcard →
LITE08-11postBULLISH±9.1%+13.6%hitcard →
ASTS08-10postBULLISH±11.0%+4.2%hitcard →
RKLB08-10postBEARISH±10.9%-0.0%hitcard →
QBTS08-06preBULLISH±8.6%-9.3%misscard →
RGTI08-06postBULLISH±7.6%+8.5%hitcard →
CRCL08-05preBULLISH±9.5%+0.1%hitcard →
UBER08-05preBULLISH±5.0%-5.3%misscard →
IONQ08-05postBULLISH±10.2%-0.5%misscard →
OXY08-05postBULLISH±4.6%+4.1%hitcard →
AMD08-04postBULLISH±7.6%-7.0%misscard →
CVX07-31preBEARISH±2.1%+2.4%misscard →
MA07-30preBULLISH±2.4%+2.5%hitcard →
AMZN07-30postBULLISH±6.7%+15.3%hitcard →
MSFT07-29postBULLISH±6.1%+15.5%hitcard →
BA07-28preBULLISH±4.0%+4.8%hitcard →
STX07-28postBULLISH±12.5%+2.3%hitcard →
INTC07-23postBEARISH±10.4%-7.9%hitcard →
TSLA07-22postBEARISH±5.2%-14.5%hitcard →
TSM07-16preBULLISH±3.4%-2.3%misscard →
NFLX07-16postBEARISH±8.1%-7.3%hitcard →
MS07-15preBULLISH±3.1%+0.4%hitcard →
22 directional calls out of 52 reports scanned — on the other 30 the model had no edge and stayed quiet, so they are excluded rather than counted as free wins.

How it's built

  • Implied — the at-the-money straddle on the first expiry after the report, over spot. That is literally what the market charges you to own the move.
  • Typical — mean absolute reaction across the last 9 prints, from the tape.
  • Session alignment — a pre-market report moves the stock that day; an after-close report moves it the next. Measure both the same way and a fairly-priced option looks 4× too expensive. Most sources do exactly that.
  • Silent weeks — if fewer than two covered names report, no board is published rather than padding one out.
CadenceSunday, week ahead
History on file69 tickers
Reactions per namelast 8–9 reports
RICH thresholdimplied ≥ 1.25× typical
CHEAP thresholdimplied ≤ 0.95× typical
Sourcelive option chain + tape

Home/Products/Structure Read

Structure Read

The chart the desk actually trades from

Not a price line. Zig-zag pivots, the break triggers on both sides, measured targets, the volume-at-price magnet profile on the right edge, and the read written out underneath. 6 names below are the full desk chart; all 76 covered tickers are searchable.

NVDA
MU
TSLA
AMD
META
INTC
Full desk charts refresh daily for members; the searchable levels here update with the nightly run.

Home/Products/Research

Research

Institutional flow · Q2 2026

Rebuilt from SEC's raw 13F filings rather than a vendor feed. Net flow is change in share count × quarter-end price — change in reported value just tells you the stock went up.

13F flows
  • Splits restated from the holders themselves, not a data feed.
  • Entity migration excluded — a manager re-registering is not buying.
  • CUSIP changes and share classes netted by issuer.
  • Misreported rows dropped against the filers' own consensus price.
Panel1,410 managers
Holdings parsed4.77M rows
Basissame roster, both quarters
Verifiedreconciled to the tape

Filing dredge · who got the $100B

SEC filings are the original record, public before anyone writes them up. This study read 124 companies' own 10-Qs to find where the struck-down tariff refunds actually landed.

Tariff refunds
  • Form 4, code P only — an open-market purchase with the insider's own cash. Grants, option exercises and scheduled 10b5-1 sales say nothing about conviction.
  • Schedule 13D — somebody crossing 5% with intent to influence.
  • Scanned twice a day, straight from EDGAR full-text.
Cadence6:20am + 3:20pm PT
Threshold$400k+ open-market buys
Latest scan15 buys · 15 stakes
SourceEDGAR, no vendor

Home/Products/龙气🤖 Algo

Balder-algo-logs · 龙气🤖

The short book — you see what it buys

Positions last from a few hours to a few days. Entries, adds and exits are reported as they happen, and half an hour after the close one card sums up every trade of the day — not the good ones picked afterwards, all of them.

Closed trades
42
Win rate
67%
Average
+1.71%
Best / worst
+11.2% / -8.7%
Open now
9
All 42 closed trades, winners and losers alike.

Two strategies, run independently

They are trying to do different things, so they never interfere with each other.

Oversold bounce · RSI bounced11 trades · 91% win
Momentum · Alpha Emerged31 trades · 58% win
Holding periodhours – days
Reportinglive + after-close card
The bounce strategy takes fewer trades and wins more often; the momentum strategy takes many more and each one is thinner. Both numbers are published — neither is hidden behind the other.
龙气🤖 daily summary card

Every closed trade

Newest first. The record is complete because each entry was published before the outcome was known.

SymbolStrategy OpenedClosed EntryExitReturn
GOOGLMomentum08-1208-14342.81348.98+1.8%
QBTSMomentum08-1008-1320.6021.17+2.8%
NFLXMomentum08-1208-1374.3375.79+2.0%
IONQMomentum08-1308-1345.5546.13+1.3%
TSLAOversold bounce08-1008-13327.74339.96+3.7%
WDCMomentum08-0608-12423.31452.60+6.9%
MUMomentum08-0608-12851.34904.46+6.2%
TSMMomentum08-0708-12418.07428.06+2.4%
STXMomentum08-1008-12816.99885.94+8.4%
IONQMomentum08-1008-1242.6244.34+4.0%
ARMMomentum08-1208-12273.26268.26-1.8%
MCDMomentum08-1108-12271.94274.80+1.1%
HOODOversold bounce08-1008-1293.0794.91+2.0%
MRVLMomentum08-0408-11219.71210.57-4.2%
GOOGLMomentum08-1108-11353.41349.59-1.1%
CRCLMomentum08-1008-1166.6170.29+5.5%
NFLXMomentum08-1108-1175.9276.72+1.1%
ARMMomentum08-1008-11270.64267.39-1.2%
INTCMomentum08-0708-1099.3396.98-2.4%
MCDMomentum08-0708-10275.54272.34-1.2%
ORCLMomentum08-0408-07146.74145.16-1.1%
STXMomentum08-0708-07827.41780.91-5.6%
ARMMomentum08-0708-07282.50278.97-1.2%
BEMomentum08-0408-07230.75215.80-6.5%
IONQMomentum08-0508-0740.2343.07+7.1%
RGTIMomentum08-0508-0716.8917.88+5.9%
TSLAOversold bounce08-0408-07322.06328.57+2.0%
STXMomentum08-0408-06863.59788.72-8.7%
IBMMomentum08-0508-06234.50231.47-1.3%
AAPLOversold bounce08-0308-06307.30312.40+1.7%
TSMMomentum08-0408-05416.20420.61+1.1%
WDCMomentum08-0308-05515.51561.49+8.9%
ASTSMomentum08-0308-0463.5170.62+11.2%
NOKOversold bounce07-3108-049.449.92+5.1%
CRCLMomentum07-3108-0362.0158.85-5.1%
INTCMomentum08-0308-0387.7890.67+3.3%
IBMOversold bounce07-2908-03224.37226.30+0.9%
SPCXOversold bounce07-2908-03115.40114.47-0.8%
TSLAOversold bounce07-2908-03305.80322.07+5.3%
SPYOversold bounce07-3108-03740.37757.69+2.3%
QQQOversold bounce07-3007-31678.30693.29+2.2%
MRVLOversold bounce07-3007-31178.11192.00+7.8%

Home/Products/Balder's Position

Balder’s Position

The long book — every name, in and out

Uptrend trend-following. Published after the close, so you can take it in the after-hours session or the next morning — the holding period is long enough that the first few minutes do not decide the trade. Every position carries its reasoning.

Disclosed on the way in and on the way out — which is why the table below is complete by construction. There is no version of it with the losers removed.

Positions
20
Closed up
70%
Average
+8.3%
Best
RGTI +30.2%
Worst
WDC -5.3%
Balder's Position book card
Strategyuptrend trend-following
Publishedafter every close
Tradeableafter hours or next day
Each position carriesreasoning + analysis
Book opened2026-07-28
Entries and exitsall disclosed
SymbolInOutEntryLast / exit ReturnHeld
RGTIOPEN14.4618.82+30.2%
QBTSOPEN17.6821.17+19.7%
ASTSOPEN55.4570.98+28.0%
IONQOPEN36.5246.26+26.7%
IBMOPEN225.71234.32+3.8%
NFLXOPEN73.5378.16+6.3%
NVDAOPEN226.04225.16-0.4%
BRK-B08-0308-15517.22505.97-2.2%12d
GOOGL08-0608-13357.54346.03-3.2%7d
MCD08-0608-12275.65275.04-0.2%6d
INTC07-2908-1281.88102.50+25.2%14d
ARM07-3008-12241.54274.30+13.6%13d
WDC07-2908-11462.04437.67-5.3%13d
MU08-0308-11829.50861.22+3.8%8d
TSM08-0308-11406.11420.79+3.6%8d
STX07-2808-11747.30821.22+9.9%14d
BE07-3008-10209.63212.39+1.3%11d
UNH07-2908-10420.57408.38-2.9%12d
MRVL08-0608-10210.54213.69+1.5%4d
CRCL07-3108-1062.6166.25+5.8%10d
Disclosed research positions, marked at the close. Past results do not predict future results.

Handbook · 订阅使用说明书

How to use the subscription

Three channels, identical content — pick whichever is easiest. If you subscribe on X, do it in a web browser: subscribing inside the iOS app adds Apple's 30% cut.

X · subscribe on the web
$5 /month
Unlocks the red channel. Subscribe in a browser — an in-app purchase loses 30% to Apple.
Subscribe on X →
Venmo · recommended
$10 /month
Put your email in the payment note — enrolment is automatic and everything arrives by email. $30 buys three months.
Subscribe on Venmo →
Substack
$10 /month
Billed through Substack; the same content arrives by email.
Subscribe on Substack →

1 · Balder-algo-logs — the short book

Close to a follow-along feed: you see what it buys, as it buys it. It runs two strategies, oversold bounce and momentum, holds from a few hours to a few days, reports every trade live, and posts one summary card half an hour after the close.

The two strategies run independently and never interfere — they are trying to do different things. Every closed trade is here →

Balder algo-logs daily summary

2 · Balder’s Position — the long book

Uptrend trend-following. It goes out after the close, so you can trade it in the after-hours session or the next morning — the horizon is long enough that the first few minutes do not decide it. Every position comes with its reasoning and analysis; ask if any part of it isn't clear.

Disclosed on entry and on exit, so the record is complete — winners and losers both. See the record →

Balder's Position book card

3 · Earnings Radar

The badge in the top-right corner is the whole read:

Green — the model expects up
Red — the model expects down
Grey — coin-flip, the model is making no call at all

Grey does not mean "unsure". It means the model declined to act, and those are excluded from the record rather than scored as free wins. The scored history is here →

Members can request a Structure Read or an Earnings Radar for a specific ticker. A name added on request usually comes back coin-flip, because the system has no history on it yet — that is expected, not a fault.
Earnings Radar board

4 · What is free

The SPX cone and the 24/7 board are free to everyone right now — no subscription needed.

24/7 board →   SPX probability cone →   Free Discord →

5 · What comes next

More tutorials, more strategies, more products — the research loop runs continuously and what survives gets published.

Everything here is NFA — not financial advice. Please don't ask for entry prices, position sizes or timing.
algo-logs · shortlive + after-close card
Position · longafter every close
Earnings Radarearnings weeks · red/green/grey
Structure Readon request for members
SPX / 24-7 boardfree
All three channelsidentical content
Join — $10/month Get the free read instead →

Membership · Beta

Trade with Balder

One price, three ways to pay, identical content on every one of them — the marked book, the cone, the radar, and the reasoning behind each call. What you get, in detail →

$10 / month on Venmo

Also on X at $5 (subscribe on the web, not in the app — the app adds Apple's 30%) and Substack at $10. All three carry identical content. Full handbook →

  1. Send $10 for each month you want on Venmo — $30 gets you three.
  2. Put your email address in the payment note. That is the only way we know where to send you.
  3. The system reads the payment and enrols you automatically — usually within half an hour, no forms.
Pay on Venmo → @Balder0405
No email in the note means no way to reach you — that is the one step that cannot be skipped.
Beta pricing while the site is being built out.

Not ready to pay? The daily posts are free on X, Substack and Discord.
Balder
Daily
Balder's Position letter + marked book
Daily
SPX 24×7 cone + structure reads
Weekly
Earnings Radar board
As filed
Insider buys & 13D stakes

404

That page isn’t here.

The address you followed doesn’t match anything on this site — most likely a link from before the pages moved to their own addresses. Everything the desk publishes is one click away.