Study finds cheaper claim verification carries higher unsupported-claim acceptance
Researchers report in a preprint that combining a cheaper claim verifier with a frontier language model scored 74.10 at USD 2.92 per thousand claims, against 73.83 at USD 8.93 for the frontier model alone. The system sends some cl...
Researchers report lower-cost training for LLM information gathering
Researchers report in a preprint that training language models to select questions using information-gain rewards improved performance on Twenty Questions at substantially lower computational cost than the experimental-design base...
Researchers report 66 faults in six software security testing tools
Researchers report that LLM4SAST, a framework for testing software security scanners, identified 66 unique faults across six tools. Developers confirmed or fixed 32 after receiving reports, according to the arXiv preprint. The fr...
Researchers report lower quantum circuit resource needs with LLM-guided search
Researchers report in an arXiv preprint that a search framework using large language models discovered quantum circuits requiring fewer Toffoli gates and qubits than prior designs in seven of eight tasks. The models propose circui...
AWS expands T8i compute instances to São Paulo
AWS has made its EC2 T8i instances available in its South America region in São Paulo, expanding access to computing designed for workloads with low to moderate processor use. The instances use custom Intel Xeon 6 processors and c...
AWS adds timestamp-based reading to DynamoDB Streams
AWS has added timestamp-based reading to DynamoDB Streams, allowing applications to start with the first record written at or after a chosen time. Previously, consumers could start only with the oldest retained record, up to 24 ho...

