Solidity
PulseAugur coverage of Solidity — every cluster mentioning Solidity across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Claude 3.5 Sonnet leads in AI code auditing benchmark, beating GPT-4o and Llama 3
A recent benchmark evaluated GPT-4o, Claude 3.5 Sonnet, and Llama 3 70B for their effectiveness in automated code auditing, specifically for detecting vulnerabilities in smart contracts. Claude 3.5 Sonnet emerged as the…
-
Neurosymbolic framework reconstructs LLM outputs using Combinatory Categorial Grammar
Researchers have proposed a neurosymbolic framework to reconstruct the outputs of large language models (LLMs) into typed compositional derivations using Combinatory Categorial Grammar (CCG). This approach, while not cl…
-
Solidity compiler flaws uncovered by 3-year fuzzing effort
Researchers have identified 25 miscompilation bugs within the Solidity compiler, which is crucial for developing Ethereum smart contracts. These vulnerabilities were discovered over a three-year period using a specializ…
-
Open-source AI tool Fizz automates Solidity smart contract security
An open-source AI tool named Fizz has been introduced for Solidity developers, aiming to automate smart contract security. Fizz can cover up to 80% of state-based fuzzing tests with a single prompt. It also assists with…
-
AI coding agents outpace human auditors for smart contract verification
AI coding agents like Cursor, Claude Code, and Codex are now generating Solidity code faster than human auditors can verify it. This shift in 2026 creates a bottleneck in the verification process, leading audit firms to…
-
AI Platform Combines Deepfake Detection with Blockchain Evidence
Researchers have developed a new platform called DeepFake Forensics AI, designed to combat the growing threat of synthetic media in legal and forensic settings. This system integrates multi-modal detection capabilities …
-
New SCDBench benchmark reveals LLM struggles with smart contract decompilation
A new benchmark called SCDBench has been introduced to evaluate Large Language Models (LLMs) used for smart contract decompilation. The benchmark includes a dataset of 600 real-world Solidity contracts with paired bytec…
-
Replit launches Solidity and Rust templates for easier development
Replit has launched new development templates for Solidity and Rust, aiming to lower the barrier to entry for these programming languages. The Solidity template is designed to simplify the creation and deployment of sma…