GoKawiil
Tech News
Anthropic released Claude Sonnet 5.5, the second model in its Claude 5.5 lineup after Opus 5.5. The company says it runs over 30% faster and costs up to 30% less per task than Sonnet 5, while keeping the same per-token pricing, and jumps from 10.3% to 70.6% on the Terminal-Bench 4.0 agentic coding evaluation. A third model, Claude Haiku 5.5, is planned for release in the coming weeks.
Anthropic released Opus 5.5, an update to Claude aimed at enterprise tasks like coding, financial analysis and business work, claiming better agentic coding benchmarks than GPT-6 Astra and reduced token pricing compared to Opus 5. OpenAI simultaneously released GPT-6 Sol and GPT-6 Luna, cheaper successors to GPT-5.6 that the company says cut factual errors roughly in half and match rival Fable 5.1's coding performance at lower cost.
A blog post recounts Warren Zevon's October 2002 appearance on The Late Show with David Letterman, made while Zevon was living with terminal cancer. The writer highlights Zevon's remark to Letterman about needing to 'enjoy every sandwich' and describes rediscovering the clip years later via a YouTube recommendation while eating a sandwich during a travel layover.
The author recounts struggling for years to move beyond single terminal commands, unable to chain logic like conditionals, loops, or piping output between programs. Over time they gradually learned shell scripting well enough to write basic conditional scripts, such as one checking npm install exit codes and printing custom error messages.
Sigabrt.dev is a new cronjob monitoring service that lets users check endpoint status, schedules and recent events directly through an SSH-based terminal UI rather than a web dashboard. Users add their SSH public key in settings and connect via 'ssh sigabrt.dev' to view their monitored jobs. The product is described as an early, read-only work in progress, with the developer soliciting feedback on future features.
Australian fintech Zeller has released Terminal 2, an affordable all-in-one point-of-sale device built and designed domestically. The product won Best Design in Asia Pacific at the 2026 Innovation by Design Awards, recognized for reimagining payment hardware as a consumer-facing product rather than purely functional equipment.
A developer released txt, a lightweight, keyboard-driven text editor built to run directly in the terminal without configuration or a modal input system. It uses tree-sitter for syntax highlighting across many languages, supports code folding, and includes a fuzzy symbol picker for navigating functions and classes within a file.
A developer released Toast, an open-source terminal-based code editor available via Homebrew, positioned as a preconfigured alternative to Vim, Neovim, and Emacs. It ships with managed language server installs, tree-sitter syntax highlighting for languages like Go, Rust, and Python, a file tree sidebar with git status, multi-tab editing, spell checking, and go-to-definition support, all working out of the box without manual configuration.
gPTY is a new open-source project that pairs the Godot game engine with Rust to create a PTY-based terminal multiplexer featuring a resizable tiling grid for panes like terminals, code viewers, and file trees. It exposes a JSON-RPC/CLI/MCP control interface so AI agents and scripts can spawn panes, inject text, and read output programmatically instead of scraping terminal UIs. It also includes a regex-based 'concept engine' that captures and routes terminal output into other panes, plus persistence via SQLite/JSON for scrollback, settings, and workspaces.
RTK, a popular tool with over 79,000 GitHub stars that compresses terminal output before AI coding agents read it, has been marketed as a way to cut AI coding costs, with one viral post claiming up to 60% token savings. But independent benchmark testing using Terminal-Bench 2.1 across 1,740 task attempts found mixed results: costs dropped 5% for one model setup but rose 5% for another, contradicting the widely shared savings figures.
Herdr Studio launches as a lightweight interface that connects to a developer's existing runtime, letting agents continue running in genuine terminal sessions managed by Herdr. The company says the tool can be set up and running in three steps, positioning it as an add-on rather than a replacement for current infrastructure.
Cognition released SWE-2, a coding model built by post-training on a 2.8-trillion-parameter Kimi K3 base with 104B active parameters, marking its first RL push into the multi-trillion-parameter range. The model posts a class-leading 92.8 on Terminal-Bench 2.1 and competitive FrontierCode scores at lower cost than rivals like Claude Fable 5.1 and GPT-6 Astra, but falls well behind both on the harder Terminal-Bench 4.0 benchmark (27.3 vs 55.8 and 57.9). SWE-2 is closed-weight and available now through Devin Desktop and CLI, with no local deployment option.