
## Slash Pages

<div class="home-slashes"><a href="/carry/" class="home-slash-link">/carry/</a><a href="/verify/" class="home-slash-link">/verify/</a><a href="/top4/" class="home-slash-link">/top4/</a><a href="/yep/" class="home-slash-link">/yep/</a><a href="/nope/" class="home-slash-link">/nope/</a><a href="/ai/" class="home-slash-link">/ai/</a><a href="/wants/" class="home-slash-link">/wants/</a><a href="/tinyapps/" class="home-slash-link">/tinyapps/</a><a href="/analytics/" class="home-slash-link">/analytics/</a><a href="/now/" class="home-slash-link">/now/</a><a href="/start/" class="home-slash-link">/start/</a><a href="/colophon/" class="home-slash-link">/colophon/</a><a href="/markata/" class="home-slash-link">/markata/</a><a href="/feeds/" class="home-slash-link">/feeds/</a><a href="/thoughts/" class="home-slash-link">/thoughts/</a><a href="/about/" class="home-slash-link">/about/</a></div>

## Latest [Thoughts](/thoughts/)

<div class="feed h-feed">
<div class="posts posts-list">

<article class="card card-link h-entry">
<header class="card-header">
<div class="card-link-wrapper">

<div class="card-link-content">
<a href="/thought-979/" class="card-title p-name u-url">💭 A love letter to Pi | Lucas Meijer</a>

<a href="https://www.youtube.com/watch?v=fdbXNWkpPMY" class="card-domain" rel="noopener noreferrer" target="_blank">www.youtube.com</a>
<data class="u-bookmark-of" value="https://www.youtube.com/watch?v=fdbXNWkpPMY" hidden></data>

</div>
</div>
</header>

<div class="card-body">
<div class="card-excerpt p-summary"><p>I hate how he called out terminal user interfaces as shit&hellip; then proved web interfaces to be superior. Damn him. I love working from my terminal, but having ai prove itself through html reports including video, image, metrics, charts, and text is goated. Rethinking yourself has the bottleneck not the orchestrator feels real. Validating the work is hard, theres a shift right now and everyone is trying to figure it out. Lucas&rsquo;s technique is a little bit of be lazy and tell it to prove itself to you, so as you juggle your 15 agents you have a nice report to read.</p></div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-15T16:12:33Z">April 15, 2026</time>

<div class="card-tags">

<a href="/tags/ai/" class="tag p-category">ai</a>

<a href="/tags/llm/" class="tag p-category">llm</a>

<a href="/tags/agents/" class="tag p-category">agents</a>

<a href="/tags/thought/" class="tag p-category">thought</a>

</div>

</footer>
</article>

<article class="card card-link h-entry">
<header class="card-header">
<div class="card-link-wrapper">

<div class="card-link-content">
<a href="/thought-978/" class="card-title p-name u-url">💭 How Claude Code’s Creator Starts EVERY Project - YouTube</a>

<a href="https://www.youtube.com/watch?v=KWrsLqnB6vA" class="card-domain" rel="noopener noreferrer" target="_blank">www.youtube.com</a>
<data class="u-bookmark-of" value="https://www.youtube.com/watch?v=KWrsLqnB6vA" hidden></data>

</div>
</div>
</header>

<div class="card-body">
<div class="card-excerpt p-summary"><p>This is a really good guide, with quite a few good nuggets. I need to try deleting my AGENTS.md and rebuilding it from scratch more often. I liked how he talked about having agents prove their work and tell them up front how they will be judged. What I didn&rsquo;t care for so much was the feeling that a lot of the rules go in markdown, thats not a rule, thats a suggestion. Rules should be deterministic. They should be tests and linters that ensure they are followed. Suggestions are good, but dont trust the agents to always follow them. And don&rsquo;t trust that they wont change your rules, keep them honest.</p></div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-15T16:07:26Z">April 15, 2026</time>

<div class="card-tags">

<a href="/tags/llm/" class="tag p-category">llm</a>

<a href="/tags/ai/" class="tag p-category">ai</a>

<a href="/tags/agents/" class="tag p-category">agents</a>

<a href="/tags/thought/" class="tag p-category">thought</a>

</div>

</footer>
</article>

<article class="card card-link h-entry">
<header class="card-header">
<div class="card-link-wrapper">

<div class="card-link-content">
<a href="/thought-977/" class="card-title p-name u-url">💭 POV: Growing up as a Millennial be like 🤣 AC:@mikemancusi #mil...</a>

<a href="https://www.youtube.com/shorts/qH3KH-q_tGE" class="card-domain" rel="noopener noreferrer" target="_blank">www.youtube.com</a>
<data class="u-bookmark-of" value="https://www.youtube.com/shorts/qH3KH-q_tGE" hidden></data>

</div>
</div>
</header>

<div class="card-body">
<div class="card-excerpt p-summary"><p>Feeling this today, feels like everything continues to get worse. Trying to be more positive, and its hard.</p></div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-15T16:02:46Z">April 15, 2026</time>

<div class="card-tags">

<a href="/tags/random/" class="tag p-category">random</a>

<a href="/tags/thought/" class="tag p-category">thought</a>

</div>

</footer>
</article>

<article class="card card-link h-entry">
<header class="card-header">
<div class="card-link-wrapper">

<div class="card-link-content">
<a href="/thought-976/" class="card-title p-name u-url">💭 Write It First, Then Let AI Drive - Kenneth Reitz</a>

<a href="https://kennethreitz.org/essays/2026-04-12-write_it_first_then_let_ai_drive" class="card-domain" rel="noopener noreferrer" target="_blank">kennethreitz.org</a>
<data class="u-bookmark-of" value="https://kennethreitz.org/essays/2026-04-12-write_it_first_then_let_ai_drive" hidden></data>

</div>
</div>
</header>

<div class="card-body">
<div class="card-excerpt p-summary"><p>Interesting take by Kenneth Reitz. Not quite sure how I feel about it anymore. It kinda hurts, but I&rsquo;m not sure if code aesthetics matter as much as the product anymore. I cared when I was the one editing, but at this point I&rsquo;m not doing a lot of edits by hand. Do these aesthetics affect the final products that users use, Not sure. AI makes me sad.</p></div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-14T20:05:11Z">April 14, 2026</time>

<div class="card-tags">

<a href="/tags/llm/" class="tag p-category">llm</a>

<a href="/tags/ai/" class="tag p-category">ai</a>

<a href="/tags/thought/" class="tag p-category">thought</a>

</div>

</footer>
</article>

<article class="card card-link h-entry">
<header class="card-header">
<div class="card-link-wrapper">

<div class="card-link-content">
<a href="/thought-975/" class="card-title p-name u-url">💭 I am slowly coming around to AI assisted programming.</a>

<a href="https://x.com/ThePrimeagen/status/2043861800819761382" class="card-domain" rel="noopener noreferrer" target="_blank">x.com</a>
<data class="u-bookmark-of" value="https://x.com/ThePrimeagen/status/2043861800819761382" hidden></data>

</div>
</div>
</header>

<div class="card-body">
<div class="card-excerpt p-summary"><p>If agents make prime a bit faster, what does that mean for the rest of us mortals?</p></div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-14T15:17:09Z">April 14, 2026</time>

<div class="card-tags">

<a href="/tags/llm/" class="tag p-category">llm</a>

<a href="/tags/ai/" class="tag p-category">ai</a>

<a href="/tags/thought/" class="tag p-category">thought</a>

</div>

</footer>
</article>

</div>
</div>

[See all thoughts &rarr;](/thoughts/){.home-see-more}

## Recent [Pings](/pings/)

<div class="feed h-feed">
<div class="posts posts-list">

<article class="card card-note h-entry">
<header class="card-header">

<h3 class="card-title p-name"><a class="u-url" href="/ping-50/">Ping 50</a></h3>

</header>

<div class="card-body">
<div class="card-content">

<div class="card-text p-content">I wrote code by hand today... I was out of tokens</div>

</div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-15T21:11:58Z">April 15, 2026</time>

<a href="/ping-50/" class="card-link">View</a>
</footer>
</article>

<article class="card card-note h-entry">
<header class="card-header">

<h3 class="card-title p-name"><a class="u-url" href="/ping-49/">Ping 49</a></h3>

</header>

<div class="card-body">
<div class="card-content">

<div class="card-text p-content">What&#39;s going to happen to all of our software when Anthropic Mythos finds all
of the 0 day vulnerabilities? Will everything depending on the bugs break?
Will it be possible to fix them cleanly? Will we all get pwnd when the bad
actors get access to them before everything is patched? Will LTS Operating
Systems Die?</div>

</div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-13T16:12:04Z">April 13, 2026</time>

<span class="webmention-counts">

</span>

<a href="/ping-49/" class="card-link">View</a>
</footer>
</article>

<article class="card card-note h-entry">
<header class="card-header">

<h3 class="card-title p-name"><a class="u-url" href="/ping-48/">Ping 48</a></h3>

</header>

<div class="card-body">
<div class="card-content">

<div class="card-text p-content"></div>

</div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-08T16:12:32Z">April 8, 2026</time>

<span class="webmention-counts">

</span>

<a href="/ping-48/" class="card-link">View</a>
</footer>
</article>

<article class="card card-note h-entry">
<header class="card-header">

<h3 class="card-title p-name"><a class="u-url" href="/ping-46/">What is this job anymore</a></h3>

</header>

<div class="card-body">
<div class="card-content">

<div class="card-text p-content">The job of writing code is dying, models are getting better, the average person
will have their average features implemented in average ways with no effort by
agents, the writing is on the wall. We are still trying to review most of the
critical code, this is slowing us down, is it really stopping any bugs or
giving us any more familiarity with the product, marginally.

The time is now to grease up your UAT, testing, deployment pipelines. Dont let
agents delete entire regions. Review your backup and restore strategy, you do
have a DR plan right?

Things are changing fast, the best of us are still better than the clankers.
Most of us have more context than the clankers. Most of us have more intuition
of what and where to implement fixes. Context windows and memory will be
solved problems. Your DR plan, UAT, testinng and QA environments will not come
for free, you need to make them, and deeply integrate them into your processes.</div>

</div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-03T20:44:55Z">April 3, 2026</time>

<span class="webmention-counts">

</span>

<a href="/ping-46/" class="card-link">View</a>
</footer>
</article>

<article class="card card-note h-entry">
<header class="card-header">

<h3 class="card-title p-name"><a class="u-url" href="/ping-47/">Ping 47</a></h3>

</header>

<div class="card-body">
<div class="card-content">

<div class="card-text p-content"></div>

</div>
</div>

<footer class="card-meta">

<time class="dt-published" datetime="2026-04-02T21:33:20Z">April 2, 2026</time>

<span class="webmention-counts">

</span>

<a href="/ping-47/" class="card-link">View</a>
</footer>
</article>

</div>
</div>

[See all pings &rarr;](/pings/){.home-see-more}
