A benchmarking study tested several GGUF quantizations of the Qwen3.8 27B model against benchmarks including GPQA Diamond, IFBench, and Terminal-Bench 2.1. The 17GB Q4_K_M version performed on par with the full 55GB BF16 model on coding tasks and fits on a consumer 24GB GPU, while the smallest 6.2GB 1-bit version dropped to near-random accuracy on reasoning tasks, with longer reasoning chains making results worse.
quesma.com
· 2026-09-08
On September 29, 2016, a New Jersey Transit train failed to stop and crashed into Hoboken Terminal at about 21 mph, killing one person and injuring 110. Three months later, a Long Island Railroad train had a nearly identical failure at Atlantic Terminal in Brooklyn, injuring 108 with no deaths. NTSB investigators found both engineers had undiagnosed sleep apnea and that neither train had systems capable of intervening before the crash.
practical.engineering
· 2026-09-01
A widely discussed Hacker News post argued developers should favor GUIs over terminal user interfaces (TUIs), sparking pushback from commenters who claimed TUIs are superior because they're keyboard-driven. The author counters that keyboard-driven design isn't exclusive to TUIs, pointing to guidelines like GNOME's HIG that explicitly require GUIs to support full keyboard navigation.
ckardaris.com
· 2026-08-28
Stanford researchers, working with the Terminal-Bench team and scientists across disciplines, launched Terminal-Bench-Science, a benchmark testing AI agents on real scientific research workflows. The initial version includes 70 tasks spanning life, physical, Earth, mathematical, and engineering sciences, with Claude Opus 5 running Claude Code topping the leaderboard at a 30% resolution rate.
terminal-bench-science.ai
· 2026-08-28
A developer released hrdx, an experimental open-source terminal multiplexer written in Go, designed around running multiple AI coding agents like Codex CLI and Claude Code side by side. It organizes projects as workspaces with tabs and real PTY-backed terminal panes, using status indicators to show which agents are actively working or have finished.
github.com
· 2026-08-27
GoKawiil