Joshua
1.6K posts


Introducing Caesar Research for agents. Agents work better with real-time research. A single install command for all agents and no account needed. Get started: caesar.org/agents


LLMs process text from left to right — each token can only look back at what came before it, never forward. This means that when you write a long prompt with context at the beginning and a question at the end, the model answers the question having "seen" the context, but the context tokens were generated without any awareness of what question was coming. This asymmetry is a basic structural property of how these models work. The paper asks what happens if you just send the prompt twice in a row, so that every part of the input gets a second pass where it can attend to every other part. The answer is that accuracy goes up across seven different benchmarks and seven different models (from the Gemini, ChatGPT, Claude, and DeepSeek series of LLMs), with no increase in the length of the model's output and no meaningful increase in response time — because processing the input is done in parallel by the hardware anyway. There are no new losses to compute, no finetuning, no clever prompt engineering beyond the repetition itself. The gap between this technique and doing nothing is sometimes small, sometimes large (one model went from 21% to 97% on a task involving finding a name in a list). If you are thinking about how to get better results from these models without paying for longer outputs or slower responses, that's a fairly concrete and low-effort finding. Read with AI tutor: chapterpal.com/s/1b15378b/pro… Get the PDF: arxiv.org/pdf/2512.14982

Caesar is now publicly available for everyone. Simply sign up with your email address to start using Caesar. Access the most powerful deep research platform without a subscription. Caesar.org



$2.5 trillion wiped out in 30 minutes. That's roughly the entire market cap of crypto.

JUST IN: OpenAI is quietly building a social network and considering using biometric verification like World’s eyeball scanning orb or Apple’s Face ID to ensure its users are people, not bots. Full story: forbes.com/sites/annatong… (Photo: Florian Gaertner/Photothek via Getty Images)

Feed > Iran > ICE > Elon calling person retarded > Poland > EU > More Elon > Clawd > ICE > Trump > fake data crypto post > toly trying to sell phone > Elon please pass the rope


SUI를 기본 레이어로 사용하는 @Talus_Labs 인데 Union 및 Tria 파트너십을 통해 EVM, Solana 같은 다양한 체인으로 확장하고 있네유 체인추상화 레이어를 사용해서 에이전트가 체인에 구애받지 않고 작동하도록 설계되었거든요. Union의 ZK증명 기반 IBC는 메시지 전달을 효율적으로 하고 자산 전송이 가능하도록 ZKP를 사용해 빠른 검증을 수행하며, 탈루스의 자산을 Base나 이더리움 DEX에서 직접 거래할 수도 있어유 Tria의 BestPath AVS는 AI가 비용, 속도, 보안을 분석해서 최적의 경로를 선택할 수 있도록 해줍니다. AI에이전트들이 자유롭게 온체인 활동할 수 있도록 하는 Talus네유













