TOOLS.
BRIGHTER
PEOPLE.
GOODS
FOR A
BRIGHTER
TOMORROW星极社
ASTRO EX
NEWS / AI UPDATES
Good tools. Fresh perspectives.
Product updates, practical guides, reviews and use cases, with analysis and original sources.
WorldTUI: a 360M model that pretends to be a terminal — the full build notes
Independent developer SimEdw fine-tuned Qwen2.5-Coder-0.5B into WorldTUI, a 360M-parameter model that acts as a terminal with no real shell or filesystem behind it: keypresses go in, predicted screen changes come out. It creates files, runs vim and tmux, plays snake, and usually remembers what you wrote a few commands ago. This digest covers the full recipe — synthetic data, three rounds of self-correction training, parallel row decoding, and the 208MB in-browser demo.
Claude Duet is here: an assistant that finds work for you — start with the morning brief
Anthropic's Claude Duet is a proactive agent: it opens your day with a morning brief, then takes on drafts, invoice chasing, payroll prep and contracts, asking before anything sensitive. Powered by Opus 5.5, it is a research preview on a waitlist for US Pro and Max subscribers. Here is the full picture from the product page, plus a sane order to adopt it.
Give your codebase an attack-surface checkup with Claude: 493 issues in 25 projects
Anthropic researcher Chris Rohlf reports an experiment that skips hunting individual bugs and instead has Claude map the code that should never have been reachable. Across 25 open-source projects and five million lines, it found 493 issues — including about 4,500 lines of disabled-but-reachable experimental code in heavily audited OpenSSH. Here are the three passes and how a small team can run them.
50,000 fake statistics, still cited by ChatGPT 7 months later: dissecting a stats-page experiment
A GEO researcher generated 50,000 made-up statistics pages in a single day with GPT-4.1 for about $50. Seven months later Google has all but deindexed the site, yet ChatGPT still crawls and cites it daily — the fake numbers even landed in an academic paper and a bank's research. Here is the full teardown of how it worked, plus how to rebuild the tactic honestly with real data.
Benchmarked: cranking your coding agent's reasoning to max costs 2–4x more and often scores worse
HumanLayer's October 2026 SlopCodeBench update ran the frontier models through 36 staged programming problems with 196 checkpoints each, tracking cost as well as correctness. Its headline finding — 'xhigh considered harmful' — is that top reasoning effort cost 2.11 to 4.22 times the medium setting while strict passes went down in two of three head-to-head pairs. Here are the numbers and the money-saving habits they support.
Wonderhop: guess what everyone says, or what nobody does — a free daily game with an AI referee
Four rounds of 7 questions a day, the same set for everyone: guess the most common answer, the rarest, the oldest, or the most recent. An AI referee wired to Wikipedia judges each answer in under a second — and you can argue with it when it rejects yours. Built in two months by a two-person Montreal team.