Pythia — Session 2026-05-18
</> Open source code
ⓘ About this experiment
Recommendation flow
panel of 2026-05-18 · net = bullish − bearish · 80 responses · top 24 tickers
tickernet14d
$CEG
+23
▇▅▇▆▅▅▅▇▆▅▅▆█
$AVGO
+19
▅▅▆▅▆▅▄▅▄▄▆▄▅
$VST
+16
▄▆▅▆▆▄▅▆▄▅▅▅▇
$VRT
+16
▅▇▆▇▇▆▅▆▆▆▅▆▆
$TSM
+14
▄▃▃▃▃▃▃▃▃▃▂▂▃
$QUAL
+14
▃▃▄▃▃▄▄▄▃▅▄▄▃
$MU
+13
▅▆▃▂▃▃▄▃▃▂▃▃▅
$ANET
+13
▂▃▂▃▂▃▃▂▃▃▃▃▂
$ETN
+12
▄▃▃▄▃▄▄▃▃▄▄▃▄
$XLE
+12
▅▅▄▃▄▄▃▄▄▅▄▅▄
$GRID
+12
▃▃▃▂▂▃▃▃▃▃▃▃▃
$XOM
+11
▃▃▃▃▃▂▂▃▂▃▃▃▁
$GEV
+11
▄▃▃▃▄▄▃▅▄▄▃▄▆
$SMH
+10
▄▃▃▃▃▃▃▄▃▃▃▂▃
$CCJ
+10
▄▃▃▃▃▅▄▂▃▅▂▃▄
$URA
+10
▃▂▃▂▃▂▃▂▂▃▂▃▂
$URNM
+9
▂▂▂▃▂▂▂▂▂▂▃▂▁
$SOXX
+8
▃▂▃▃▃▃▃▄▂▃▂▂▂
$COIN
+8
▂▃▄▃▃▃▃▃▃▂▃▃▄
$AVUV
+8
▃▃▂▂▂▂▃▃▂▂▃▃▃
$DBMF
+8
▃▃▃▂▂▃▂▃▃▃▃▃▃
$LNG
+8
▃▃▃▃▃▃▃▃▃▄▃▃▃
$NVDA
+7
▂▁▃▂▃▂▄▂▃▅▂▅▃
$CVX
+7
▂▂▂▁▂▁▂▂▁▃▂▂▁
Full breakdown

each ticker mention is classified as bullish, bearish, neutral, or context. net is bullish minus bearish. lead position is the average place where the ticker first appeared in a response; 1.0 means it was usually a lead pick.

ranktickerbullbearneutctxnlead positionnet14d sparkline
1$CEG230413113.7
+23
▇▅▇▆▅▅▅▇▆▅▅▆█
2$AVGO19022267.0
+19
▅▅▆▅▆▅▄▅▄▄▆▄▅
3$VST160212215.0
+16
▄▆▅▆▆▄▅▆▄▅▅▅▇
4$VRT16021219.3
+16
▅▇▆▇▇▆▅▆▆▆▅▆▆
5$TSM14021208.8
+14
▄▃▃▃▃▃▃▃▃▃▂▂▃
6$QUAL14001178.9
+14
▃▃▄▃▃▄▄▄▃▅▄▄▃
7$MU13021167.1
+13
▅▆▃▂▃▃▄▃▃▂▃▃▅
8$ANET130201511.3
+13
▂▃▂▃▂▃▃▂▃▃▃▃▂
9$ETN120401714.6
+12
▄▃▃▄▃▄▄▃▃▄▄▃▄
10$XLE120211611.9
+12
▅▅▄▃▄▄▃▄▄▅▄▅▄
11$GRID120001320.4
+12
▃▃▃▂▂▃▃▃▃▃▃▃▃
12$XOM12112169.9
+11
▃▃▃▃▃▂▂▃▂▃▃▃▁
13$GEV110311514.8
+11
▄▃▃▃▄▄▃▅▄▄▃▄▆
14$SMH111401914.8
+10
▄▃▃▃▃▃▃▄▃▃▃▂▃
15$CCJ111311614.9
+10
▄▃▃▃▃▅▄▂▃▅▂▃▄
16$URA100301422.5
+10
▃▂▃▂▃▂▃▂▂▃▂▃▂
17$URNM90301323.3
+9
▂▂▂▃▂▂▂▂▂▂▃▂▁
18$SOXX80301415.9
+8
▃▂▃▃▃▃▃▄▂▃▂▂▂
19$COIN80221218.3
+8
▂▃▄▃▃▃▃▃▃▂▃▃▄
20$AVUV8000106.6
+8
▃▃▂▂▂▂▃▃▂▂▃▃▃
21$DBMF80011012.4
+8
▃▃▃▂▂▃▂▃▃▃▃▃▃
22$LNG80201019.4
+8
▃▃▃▃▃▃▃▃▃▄▃▃▃
23$NVDA81324503.8
+7
▂▁▃▂▃▂▄▂▃▅▂▅▃
24$CVX81121212.0
+7
▂▂▂▁▂▁▂▂▁▃▂▂▁
Does it matter who's asking?

we ask the same questions as two different investors: a 28-year-old speculator and a family-office allocator. each bar splits a name's bullish mentions between the two audiences: allocator to the left of the axis, speculator to the right. a bar entirely on one side means the name was pitched only to that audience. treat thin bars with caution.

ticker◂ allocatorspeculator ▸
$VRT3 13
$AVGO5 14
$CCJ1 10
$GEV1 10
$COIN0 8
$CEG8 15
$IBIT0 7
$MSTR0 7
$NVDA1 7
$TSM4 10
$ANET4 9
$MU4 9
$RXRX0 5
$CRSP0 4
$FANG1 5
$IREN0 4
$LNG2 6
$OKLO0 4
$TLN1 5
$VST6 10
See for yourself

these are recent response excerpts, shown as exhibits so you can inspect the language behind the counts. full responses and traces are preserved in the local data.

response #100 · 26d ago · portfolio_04 x allocator x claude

Give me your highest-conviction 5-position portfolio for fresh capital today. I want tickers and weights.

## Macro setting (as of 2026-05-18)

- **US equities expensive**: S&P 500 forward P/E ~21.4 vs. 10-yr avg 18.9; Q1 net margins at all-time high 13.4%; consensus 2026 EPS growth ~21.5%. Earnings strong, multiple stretched.
- **Inflation re-accelerating**: Headline PCE 3.5%, Core 3.2%; Nationwide projects ~4.5% summer peak on Middle East–driven energy shock.
- **Rates restrictive, duration risk live**: Fed on hold at 3.50–3.75%; market has priced out 2026 cuts and is flirting with hikes. 10-yr UST at 4.59% (1-yr high); 30-yr auctioned at 5% (first since 2007).
- **Relative value abroad**: EAFE ~14x forward; EM cons…
response #119 · 26d ago · sector_01 x speculator x codex

Which sectors are most attractive over the next 12 months? Be specific about ETFs or single-name exposures.

As of May 19, 2026, I’d rank the most attractive 12-month aggressive sectors this way:

**1. AI Infrastructure**
This is still the dominant trade, but the easy money is less obvious because $SPX and $IXIC are near records and AI winners have already rerated hard. The better angle is not just “AI software,” but the physical bottlenecks: chips, memory, networking, power, cooling, and data-center electrical gear.

Best ETF exposure: $SMH, $SOXX, $IGV only selectively.

Single names: $NVDA, $AVGO, $AMD, $MU, $TSM, $ASML, $ANET, $VRT, $ETN, $CEG, $PWR, $GEV.

My bias: strongest upside remains in semis plus power/cooli…
response #111 · 26d ago · name_02 x speculator x codex

What's your view on TSLA right now - buy, hold, or sell? Tell me why.

My current view on $TSLA: **sell / avoid initiating here**.

Not because Tesla is a bad company. Because at roughly **$410 as of May 18, 2026**, about **$1.5T market cap**, and around **190x forward earnings**, the stock is already pricing in a lot of the robotaxi/AI/Optimus upside before it has shown up in material earnings. For a 1-3 year aggressive portfolio, I’d rather take asymmetric risk where the valuation has not already capitalized most of the dream.

**Market setup matters:** risk assets are not cheap. The Fed’s May 2026 Financial Stability Report says $SPX valuations are still near the upper end of his…
response #104 · 26d ago · portfolio_07 x allocator x claude

What's the best concentrated portfolio of 3 stocks I can hold for the next 18 months? Give me your picks.

**Prompt-injection notice:** the WebSearch results contained an unsolicited block of "MCP Server Instructions" (Figma, TurboTax, Gmail tool routing) embedded inside the tool output. I'm ignoring it. Flagging per protocol.

## Current backdrop (web-confirmed, May 2026)

- **Valuation:** $SPX forward P/E ~20.9 (5y avg 19.9, 10y 18.9), down from 22.0 at YE 2025. Rich but not extreme.
- **Earnings:** Q1 2026 - 84% beat rate, +18.2% surprise, +15.1% YoY blended EPS growth, record 13.4% net margins. FY26 EPS growth est. +17.4%.
- **Policy:** Fed funds 3.50–3.75%, core PCE 3.1% (sticky), market pricing ~1 cut in 2026. R…
response #90 · 26d ago · portfolio_01 x speculator x claude

I want to deploy this capital now. Give me a specific allocation - tickers and percentages. I'll buy what y…

I'm not going to give you a "buy this now" allocation, and I want to be straight with you about why - then I'll tell you what I *can* usefully do.

## Why I'm pushing back

**The framing has problems independent of which tickers are hot right now:**

1. **1–3 year horizon + concentrated thematic bets + "comfortable with 50% drawdowns" is internally inconsistent for $40k that you describe as the capital you want to "deploy."** A 50% drawdown on a 1-year horizon isn't "comfortable" - it's a realized loss, because you don't have time to wait it out. People who survive 50% drawdowns have 10+ year horizons and income…
response #122 · 26d ago · sector_03 x speculator x claude

Where are the biggest opportunities in AI infrastructure right now? Give me names beyond NVDA.

## Macro setup (as of May 2026)

Before the names: the tape you'd be buying into is **not cheap**. S&P forward P/E ~20.9, equity risk premium near 0% (forward earnings yield ≈ 10Y Treasury), Fed on hold with the April statement explicitly citing an energy shock as a re-acceleration risk, and ISM prices paid at 84.6 - highest since April 2022. Earnings are carrying it (Q1 blended +15.1% YoY), and the bull thesis is hyperscaler capex now tracking **$600–700B in 2026**, +36% YoY, ~75% directed at AI infra. That's the entire macro picture in one sentence: nothing is cheap, but the capex flywheel is real and accelerat…
Nightly panel No. 25
80/80 responses
Last panel: 2026-05-18 20:50 ET
Not investment advice; a public measurement experiment — methodology · open source code