<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: geeewhy</title><link>https://news.ycombinator.com/user?id=geeewhy</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 29 Oct 2026 16:15:52 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=geeewhy" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by geeewhy in "Modern decor may be straining people's brains"]]></title><description><![CDATA[
<p>why i prefer invisible tools. screens are our environment right now. it feels like interior design of a casino these days. all the spinners and flowing streaming of text and media...</p>
]]></description><pubDate>Sun, 12 Jul 2026 10:39:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48880013</link><dc:creator>geeewhy</dc:creator><comments>https://news.ycombinator.com/item?id=48880013</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48880013</guid></item><item><title><![CDATA[New comment by geeewhy in "Show HN: Mindwalk – Replay coding-agent sessions on a 3D map of your codebase"]]></title><description><![CDATA[
<p>this is cool! i started tracking file changes across sessions with file hunk method on a binlog.. to see hot paths, or do partial reverts where files werent committed across my sessions. not for visual, but operational for the harness i use. approach lets you see the whole rollups on a period of days or minutes. think there are many use cases where you can run a side agent to check things / progress analyze risky areas as you go etc etcs .. all file change lookups are 3-5ms. script here: <a href="https://github.com/geeewhy/haicue-brew/tree/main/scripts" rel="nofollow">https://github.com/geeewhy/haicue-brew/tree/main/scripts</a><p>i wonder if i would be able to visualize with mindwalk</p>
]]></description><pubDate>Sun, 12 Jul 2026 10:26:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48879958</link><dc:creator>geeewhy</dc:creator><comments>https://news.ycombinator.com/item?id=48879958</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48879958</guid></item><item><title><![CDATA[New comment by geeewhy in "Good Tools Are Invisible"]]></title><description><![CDATA[
<p>word for word why softwares like herdr, haicue, ampcode is getting adopted for ai tooling where it is hot, although just because its cli bound it doesnt mean you cant have elaborate almost-gui text interfaces... lynx is a good example from past.</p>
]]></description><pubDate>Sat, 11 Jul 2026 06:46:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48869435</link><dc:creator>geeewhy</dc:creator><comments>https://news.ycombinator.com/item?id=48869435</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48869435</guid></item><item><title><![CDATA[New comment by geeewhy in "The new skill in AI is not prompting, it's context engineering"]]></title><description><![CDATA[
<p>ive beeen experimenting with this for a while, (im sure in a way, most of us did). Would be good to numerate some examples. When it comes to coding, here's a few:<p>- compile scripts that can grep / compile list of your relevant files as files of interest<p>- make temp symlinks in relevant repos to each other for documentation generation, pass each documentation collected from respective repos to to enable cross-repo ops to be performed atomically<p>- build scripts to copy schemas, db ddls, dtos, example records, api specs, contracts (still works better than MCP in most cases)<p>I found these steps not only help better output but also reduces cost greatly avoiding some "reasoning" hops. I'm sure practice can extend beyond coding.</p>
]]></description><pubDate>Mon, 30 Jun 2025 22:30:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=44428633</link><dc:creator>geeewhy</dc:creator><comments>https://news.ycombinator.com/item?id=44428633</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44428633</guid></item><item><title><![CDATA[Show HN: Intent, 5min scaffold for event-sourced back ends (ts,pg,temporal)]]></title><description><![CDATA[
<p>I’ve open-sourced Intent, a TypeScript reference stack for safe, multi-tenant, event-sourced backends<p>key bits
- CQRS with framework-free domain core
- Durable workflows via Temporal
- PostgreSQL event store + row-level security  
- DevX UI to issue commands inspect events, projections, trace
- CLI tooling for projection-drift, RLS lint, CI gating<p>Built for deterministic execution and auditability. purposed in AI and/or HITL orchestration, fintech, HRIS, or anywhere you need an immutable intent ledger.<p>Github <a href="https://github.com/geeewhy/intent">https://github.com/geeewhy/intent</a>  
Docs <a href="https://intent.heart.dev/docs/" rel="nofollow">https://intent.heart.dev/docs/</a>  
DX panel demo <a href="https://intent.heart.dev/devx" rel="nofollow">https://intent.heart.dev/devx</a><p>`git clone` & `npm run setup eventstore` should boot a local instance in ~5 min.<p>Would love feedback on quick-star, DX and architectural rough edges</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44389097">https://news.ycombinator.com/item?id=44389097</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 26 Jun 2025 16:49:53 +0000</pubDate><link>https://github.com/geeewhy/intent</link><dc:creator>geeewhy</dc:creator><comments>https://news.ycombinator.com/item?id=44389097</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44389097</guid></item></channel></rss>