TechiSeek

AddAdd your Listings

Research

Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity

Cohere

LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should naturally lead to a model exploiting its own discoveries.

Visit Site

Research Cohere

ResearchWhen Less is More: Investigating Data Pruning for Pretraining LLMs at ScaleCohere ResearchWhen Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMsCohere ResearchNo Need for Explanations: LLMs can implicitly learn from mistakes in-contextCohere ResearchA SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make MnemonicCohere ResearchCrosslingual Reasoning through Test-Time ScalingCohere ResearchINCLUDE: Evaluating Multilingual Language Understanding with Regional KnowledgeCohere BlogsWhy Vulnerability Scanning Isn't Enough To Protect Your AppSocket BlogsAI + a16z Podcast: Vibe Coding, Security Risks, and the Path to ProgressSocket BlogsDistributed Tracing Is a Hassle, Here's WhyThenewstack BlogsThe Agentic Infrastructure EraPulumi EventsElastic at Gartner IT Symposium/Xpo 2025 BarcelonaElastic BlogsMake a smooth shadow, friend.Css Tricks BlogsThe Origin Story of Container QueriesCss Tricks BlogsFirst Steps into a Possible CSS Masonry LayoutCss Tricks EventsAgents in ProdMotherduck BlogsFaster health data analysis with MotherDuck & PreswaldMotherduck BlogsStackAI × Cerebras: enabling the fastest inference for enterprise AI agentsCerebras BlogsBeyond AI experimentation: How to get real business valueNotion So BlogsHow I launched a viral marketing campaign using NotionNotion So BlogsWhy I joined Docker: security at the center of the software supply chainDocker