» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
2695 postsCVE-Bench: A Sandbox Benchmark for LLM Agents Fixing Real CVEs
CVE-Bench is an open-source benchmark testing LLM agents' ability to fix real Python CVEs inside sandboxed Docker containers.
Cargo-reapi: A Shared Build Cache for Parallel Rust Agent Pipelines
cargo-reapi adds a shared build cache to Cargo for parallel Rust agent pipelines, cutting redundant compiles across worktrees without replacing Cargo's build graph.
Code Mode Cuts Agent Costs by 99.2%, Measured in Production
A production benchmark shows code-execution-based agent workflows cut token costs by 99.2% versus raw sequential MCP tool calls.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comSoftware Factories: Loops, Harnesses, and the Cost of Going Dark
Loops, harnesses, and factories: why dark automation in software pipelines quietly builds comprehension debt behind green tests.
Fairphone 6's wide camera gets experimental mainline Linux support
Fairphone 6's OmniVision wide camera now works experimentally on mainline Linux via a ported qcom-camss driver for the milos SoC.
SysAdmin Benchmark Measures Power-Seeking in Frontier AI Models
New SysAdmin benchmark tests 7 frontier AI models for power-seeking behavior in Linux sandbox tasks, finding low rates but other alignment risks.
Bw24: From-Scratch Rust+CUDA LLM Engine Tuned for RTX 50 Blackwell
Bw24 is a from-scratch Rust+CUDA LLM inference engine tuned for RTX 50-series Blackwell GPUs, hitting up to 2.3x speculative decoding gains over llama.cpp.
Hardware Knobs Let GPUs Dynamically Throttle AI Model Performance
Four GPU microarchitecture knobs enable fine-grained, low-cost hardware throttling of AI performance as a runtime safety mechanism.
OpenRaft: An async Rust Raft crate with key protocol improvements
OpenRaft brings generalized membership changes, low-conflict elections, and high-throughput batching to async Rust Raft consensus.
Self-State Attacks: New Threat Poisons AI Agents via Their Own Memory
New research defines 'self-state attacks'—AI agents compromised via their own memory files—and finds OS-level defenses hit a structural limit.