Ethan Kam

search @p0 | prev @openai

[Ethan Kam @ethank_6]

muse has spoken

[George Pickett @georgepickett]

Parallel 🤝 Muse

Parallel Free Search can now supercharge your Muse agent. Just paste this:

Install Parallel’s MCP via Streamable HTTP at https://t.co/CgAi29kRU9 - no API key or OAuth needed. Verify it connects and exposes web_search and web_fetch and prefer for web search

[George Pickett @georgepickett]

Opus 5.5 pro tip:

Use Parallel web search. It’s 🆓

Opus 5.5 is the best model at using the context retrieved from web search

Just run:

claude mcp add --transport http parallel-search https://t.co/CgAi29kRU9

[Parallel Web Systems @p0]

Today we're launching Data Connectors in Parallel.

Your agents can now work with specialized third-party data through Parallel's best-in-class agentic web research APIs.

Our first partners are @AlliumLabs, @useapolloio, @Baselayerhq, @CarbonArcAI, @crunchbase, Faraday AI, @harmonic_ai, @MiddeskHQ, @Similarweb , @particle_news, @pensa_systems, and @Polymarket.

We're also launching free, opt-in access to biomedical sources including PubMed, https://t.co/hI3NfzeJmO, and ChEMBL.

[Parallel Web Systems @p0]

Claude Opus 5.5 takes the #1 spot on Parallel's Search Capability Leaderboard, with a +4.3 gain over the second-highest score from Opus 5.

[Ethan Kam @ethank_6]

Finally a model I can relate to. congrats anthropic on discovering overthinking from first principles

[Claude @claudeai]

At its default effort setting, Opus 5.5 delivers frontier results for a fraction of the cost per task, often beating other models running at their highest settings.

It also generates output more than 30% faster than Opus 5.

[Ethan Kam @ethank_6]

@aryngupt @p0 https://t.co/cNrzXjuvi8

[Ethan Kam @ethank_6]

@sportsballpm @p0 serves as a well calibrated probability model, sure you could train your own classifier to do better but jev is generally better calibrated than an llm

[Ethan Kam @ethank_6]

I had Jev predict every nfl game this sunday and walked away with a 44% profit

It found 5 bets with an edge. 4 won
$67.14 risked → $97 payout

We gave it fresh context through @p0 search, compared its win estimates on robinhood, and used the kelly criterion to size bets

[Ethan Kam @ethank_6]

@sportsballpm @p0 serves as a well calibrated probability model, sure you could train your own classifier to do better but jev is generally better calibrated than an llm

[Ethan Kam @ethank_6]

@PhillyProcess11 @p0 jev is extremely cheap, it only bills on input tokens, this is on the order of cents

[Ethan Kam @ethank_6]

@primalcowboy @p0 yes this is an llm summary of the context jev received to fit in the video

[Ethan Kam @ethank_6]

@GodfreyO_ @p0 Remotion + Astra

[Ethan Kam @ethank_6]

@0xsunny77 @p0 “mom, how did we get so rich”

[Ethan Kam @ethank_6]

@zyadelgoharyx @p0 nfa (pls don’t do this 😂)

[Ethan Kam @ethank_6]

Receipts:

[Ethan Kam @ethank_6]

For every matchup, we ran five searches using @p0’s advanced mode:
1. the matchup itself
2. news, injuries and storylines
3. matchup previews
4. team strength, offensive/defensive efficiency and roster changes
5. preseason previews and season expectations

We deduplicated the results and gave Jev the results as context

[Ethan Kam @ethank_6]

We used portfolio Kelly criterion to size bets against a $100 bankroll, maximizing expected log ending wealth.

Using Jev’s probabilities, we evaluated all win/loss combinations, assuming independent games and no ties. We priced contracts at the robinhood ask + a 2¢ fee allowance, with a $1 payout on a win and $0 otherwise.

We optimized over whole contracts with a $3 minimum per selected position.

[Ethan Kam @ethank_6]

@everythingmeta fast intelligence 🤝 fast search

[Ethan Kam @ethank_6]

Jevon’s paradox believers assemble

[Vlad @everythingmeta]

https://t.co/9G7twYF1Iw

[Ethan Kam @ethank_6]

@jaiplusplus public noice