Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

World & Business

World & Business

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

A backwards-curve joke about 'loopers' and ARC-AGI-3 · Digg

Announcement

A backwards-curve joke about 'loopers' and ARC-AGI-3

A user jokes that 'loopers' might be named for how they 'curve backwards on ARC-AGI-3.'

TLDR

A user makes a speculative joke connecting the name 'loopers' to 'curv[ing] backwards on ARC-AGI-3.'

Combined views

93.9K

4 Sources, first seen 5h ago

1K likes

Combined views

93.9K

4 Sources, first seen 5h ago

1K likes

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

5h ago

first seen 5h ago

28 comments

122 saves

83 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

28 comments

122 saves

83 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

4 Sources

@arcprizeGPT-6.1 Sol from @OpenAI on ARC-AGI (Verified): - ARC-AGI-3: 52.7%, $7.6K (standard harness), 96.4%, $4.4K (provider adapter harness) - ARC-AGI-2: 94.2%, $0.25/task - ARC-AGI-1: 98.5%, $0.06/task Its 96.4% on v3 was comparable to GPT-6 Astra's 99.9% but at a 77% lower cost.

@sanderstedOne cool thing about ARC-AGI-3 is that it measures cost until success or timeout, instead of cost of first attempt. This is arguably more aligned with real life, and shows how costly models at high efforts can counterintuitively be cheaper, by needing less iteration.

@scaling01maybe they are called loopers because they curve backwards on ARC-AGI-3

@charliermarshRT @arcprize: GPT-6.1 Sol from @OpenAI on ARC-AGI (Verified): - ARC-AGI-3: 52.7%, $7.6K (standard harness), 96.4%, $4.4K (provider adapter…

4 Sources

@arcprizeGPT-6.1 Sol from @OpenAI on ARC-AGI (Verified): - ARC-AGI-3: 52.7%, $7.6K (standard harness), 96.4%, $4.4K (provider adapter harness) - ARC-AGI-2: 94.2%, $0.25/task - ARC-AGI-1: 98.5%, $0.06/task Its 96.4% on v3 was comparable to GPT-6 Astra's 99.9% but at a 77% lower cost.

@sanderstedOne cool thing about ARC-AGI-3 is that it measures cost until success or timeout, instead of cost of first attempt. This is arguably more aligned with real life, and shows how costly models at high efforts can counterintuitively be cheaper, by needing less iteration.

@scaling01maybe they are called loopers because they curve backwards on ARC-AGI-3

@charliermarshRT @arcprize: GPT-6.1 Sol from @OpenAI on ARC-AGI (Verified): - ARC-AGI-3: 52.7%, $7.6K (standard harness), 96.4%, $4.4K (provider adapter…