Rationalsphere Search

#1A Year Late, Claude Finally Beats Pokémon 0.955

Julian Bradshaw · post · LessWrong

#2Claude Plays Pokemon: Opus 4.5 Follow-up 0.939

Josh Snider · post · LessWrong

#3Research Notes: Running Claude 3.7, Gemini 2.5 Pro, and o3 on Pokémon Red 0.916

Julian Bradshaw · post · LessWrong

#4So how well is Claude playing Pokémon? 0.915

Julian Bradshaw · post · LessWrong

#5(untitled) 0.871

Kei Nishimura-Gasparian · shortform · LessWrong

#6Is Gemini now better than Claude at Pokémon? 0.871

Julian Bradshaw · post · LessWrong

#7(untitled) 0.857

Julian Bradshaw · shortform · LessWrong

#8On getting unstuck 0.855

Joe Rogero · post · LessWrong

#9(untitled) 0.849

Daniel Kokotajlo · shortform · LessWrong

#10Claude Plays... Whatever it Wants 0.847

Adam B · post · LessWrong

#11Claude 4 You: The Quest for Mundane Utility 0.831

Zvi · post · LessWrong

#12Claude 4 You: The Quest for Mundane Utility 0.828

Zvi Mowshowitz · post · Substack

#13Claude Opus 4.6 Escalates Things Quickly 0.825

Zvi Mowshowitz · post · Substack

#14Claude Opus 4.6 Escalates Things Quickly 0.823

Zvi · post · LessWrong

#15Claude Opus 4.8: Capabilities and Reactions 0.820

Zvi Mowshowitz · post · Substack

#16Open Source LLM Pokémon Scaffold 0.818

Julian Bradshaw · post · LessWrong

#17(untitled) 0.817

Daniel Kokotajlo · comment · LessWrong

#18Claude Opus 4.8: Capabilities and Reactions 0.815

Zvi · post · LessWrong

#19Claude Opus 4.6 is Driven 0.815

HunterJay · post · LessWrong

#20(untitled) 0.805

MrCheeze · comment · LessWrong

#21Opus 4.7 Part 2: Capabilities and Reactions 0.805

Zvi Mowshowitz · post · Substack

#22Claude Opus 4.5: Model Card, Alignment and Safety 0.804

Zvi Mowshowitz · post · Substack

#23Opus 4.7 Part 2: Capabilities and Reactions 0.802

Zvi · post · LessWrong

#24Claude Opus 4.8: The System Card 0.802

Zvi Mowshowitz · post · Substack

#25Tracing the Thoughts of a Large Language Model 0.800

Adam Jermyn · post · LessWrong

#26Time to Welcome Claude 3.7 0.799

Zvi Mowshowitz · post · Substack

#27Time to Welcome Claude 3.7 0.799

Zvi · post · LessWrong

#28Claude Opus 4.5 Is The Best Model Available 0.799

Zvi Mowshowitz · post · Substack

#29Claude Code #4: From The Before Times 0.798

Zvi · post · LessWrong

#30Claude Opus 4.5: Model Card, Alignment and Safety 0.798

Zvi · post · LessWrong

#31How Anthropic’s Claude Thinks 0.798

ByteByteGo · post · Substack

#32(untitled) 0.798

Thane Ruthenis · comment · LessWrong

#33Highlights from the Claude 4 system prompt 0.798

Simon Willison · post · Substack

#34Claude Sonnet 4.5 Is A Very Good Model 0.797

Zvi · post · LessWrong

#35Claude Sonnet 4.5 Is A Very Good Model 0.796

Zvi Mowshowitz · post · Substack

#36Claude Opus 4.8: The System Card 0.796

Zvi · post · LessWrong

#37Claude Code #4: From The Before Times 0.795

Zvi Mowshowitz · post · Substack

#38Claude Opus 4.5 Is The Best Model Available 0.795

Zvi · post · LessWrong

#39On Claude 3.5 Sonnet 0.794

Zvi · post · LessWrong

#40Claude Codes #3 0.792

Zvi Mowshowitz · post · Substack

#41Claude Codes #3 0.792

Zvi · post · LessWrong

#42Surprising LLM reasoning failures make me think we still need qualitative breakthroughs for AGI 0.792

Kaj_Sotala · post · LessWrong

#43(untitled) 0.792

brambleboy · comment · LessWrong

#44Claude Code, Codex and Agentic Coding #8 0.791

Zvi · post · LessWrong

#45When you give a Claude a mouse 0.791

Ethan Mollick · post · Substack

#46On Claude 3.5 Sonnet 0.791

Zvi Mowshowitz · post · Substack

#47Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult 0.790

Simon Willison · post · Substack

#48Claude Code, Codex and Agentic Coding #8 0.789

Zvi Mowshowitz · post · Substack

#49What secret goals does Claude think it has? 0.788

loops · post · LessWrong

#50Claude Sonnet 4.5 is probably the “best coding model in the world” (at least for now) 0.788

Simon Willison · post · Substack

#51Claude Opus 4.6: System Card Part 1: Mundane Alignment and Model Welfare 0.787

Zvi Mowshowitz · post · Substack

#52The Claude 4 System Card is a Wild Read 0.787

Charlie Guo · post · Substack

#53Claude Sonnet 3.5.1 and Haiku 3.5 0.786

Zvi Mowshowitz · post · Substack

#54(untitled) 0.785

Bakkot · comment · LessWrong

#55I think "agent" may finally have a widely enough agreed upon definition to be useful jargon now 0.784

Simon Willison · post · Substack

#56GPT-5: The Case of the Missing Agent 0.784

Steve Newman · post · Substack

#57Claude Opus 4.6: System Card Part 1: Mundane Alignment and Model Welfare 0.783

Zvi · post · LessWrong

#58Claude Codes 0.783

Zvi · post · LessWrong

#59Claude Opus 4.6: System Card Part 2: Frontier Alignment 0.782

Zvi Mowshowitz · post · Substack

#60Claude Sonnet 3.5.1 and Haiku 3.5 0.782

Zvi · post · LessWrong

#61Vibing with Claude, January 2026 Edition 0.781

Gordon Seidoh Worley · post · LessWrong

#62Claude 4.5 Sonnet and Anthropic's Coding Legacy 0.780

Charlie Guo · post · Substack

#63Claude Code, Claude Cowork and Codex #5 0.780

Zvi Mowshowitz · post · Substack

#64GPT-4 Doesn't Figure Things Out, It Already Knows Them 0.780

Steve Newman · post · Substack

#65(untitled) 0.780

the gears to ascension · shortform · LessWrong

#66Claude Code, Claude Cowork and Codex #5 0.780

Zvi · post · LessWrong

#67Seeing Through the Eyes of the Algorithm 0.779

silentbob · post · LessWrong

#68GPT-5.3-Codex and Claude Opus 4.6: More System Card Shenanigans 0.779

Charlie Guo · post · Substack

#69(untitled) 0.778

Daniel Kokotajlo · comment · LessWrong

#70(untitled) 0.777

zchuang · shortform · LessWrong

#71Reinforcement learning, explained with a minimum of math and jargon 0.777

Timothy B. Lee · post · Substack

#72Opus 4.7 Part 1: The Model Card 0.777

Zvi Mowshowitz · post · Substack

#73Claude Codes 0.776

Zvi Mowshowitz · post · Substack

#74What's up with AI's vision 0.776

Joachim Bartosik · post · LessWrong

#75On Claude 3.0 0.776

Zvi · post · LessWrong

#76On Claude 3.0 0.775

Zvi Mowshowitz · post · Substack

#77Did Claude Code Lose Its Mind, Or Did I Lose Mine? 0.775

Jon Stokes · post · Substack

#78(untitled) 0.774

abramdemski · comment · LessWrong

#79Building software on top of Large Language Models 0.774

Simon Willison · post · Substack

#80Opus 4.7 Part 1: The Model Card 0.773

Zvi · post · LessWrong

#81Claude Sonnet 4.5: System Card and Alignment 0.772

Zvi Mowshowitz · post · Substack

#82(untitled) 0.772

Linch · shortform · LessWrong

#83Notes on Collaborating with Claude Opus 0.772

Nissa Seru · post · LessWrong

#84Claude Code and What Comes Next 0.771

Ethan Mollick · post · Substack

#85Claude Opus 4.6: System Card Part 2: Frontier Alignment 0.769

Zvi · post · LessWrong

#86Claude Skills are awesome, maybe a bigger deal than MCP 0.769

Simon Willison · post · Substack

#87On the geometrical Nature of Insight 0.769

Giuseppe Birardi · post · LessWrong

#88Gemma 3n, Context Engineering and a whole lot of Claude Code 0.768

Simon Willison · post · Substack

#89Dwarf Fortress and Claude's ASCII Art Blindness 0.768

Brendan Long · post · LessWrong

#90(untitled) 0.768

Mohammad Bavarian · comment · LessWrong

#91Claude Mythos: The System Card 0.768

Zvi Mowshowitz · post · Substack

#92Claude Sonnet 4.5: System Card and Alignment 0.767

Zvi · post · LessWrong

#93(untitled) 0.767

abramdemski · comment · LessWrong

#94Claude Code, Codex and Agentic Coding #7: Auto Mode 0.766

Zvi Mowshowitz · post · Substack

#95GPT 5.5, ChatGPT Images 2.0, Qwen3.6-27B 0.766

Simon Willison · post · Substack

#96Claude Mythos: The System Card 0.766

Zvi · post · LessWrong

#97(untitled) 0.765

gwern · comment · LessWrong

#98Claude Sonnet 4.6 Gives You Flexibility 0.765

Zvi Mowshowitz · post · Substack

#99Exploring Reinforcement Learning Effects on Chain-of-Thought Legibility 0.765

Julian H · post · LessWrong

#100OpenAI just unleashed an alien of extraordinary ability 0.765

Timothy B. Lee · post · Substack