<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: azuanrb</title><link>https://news.ycombinator.com/user?id=azuanrb</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 15 Jun 2026 10:34:53 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=azuanrb" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by azuanrb in "Domain expertise has always been the real moat"]]></title><description><![CDATA[
<p>I recently reviewed an app built mostly with vibe coding. The owner said it was almost ready to launch and just needed a quick check.<p>After looking through it, the database design was a mess. Some features worked, some didn’t. I explained the missing pieces and why things were breaking. Like OP said, he’s the domain expert.<p>I used billions of tokens last month alone. The tools are getting better fast. But giving AI to a domain expert doesn’t mean you no longer need software engineers.<p>A domain expert can use AI to build software. And a software engineer can use AI to learn about the domain. Both bring different expertise to the table.</p>
]]></description><pubDate>Sat, 30 May 2026 22:07:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48341073</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=48341073</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48341073</guid></item><item><title><![CDATA[New comment by azuanrb in "Orchestrating AI code review at scale"]]></title><description><![CDATA[
<p>I’ve built something similar internally, but under the hood it’s mostly codex exec + Git worktrees. The main advantage over diff-only review is that it can walk the entire codebase, trace dependencies, and understand architectural or cross-system impacts instead of only looking at the changed files. The tradeoff is that it’s noticeably more expensive to run. I'm still experimenting on it but I quite like this approach so far.</p>
]]></description><pubDate>Sat, 30 May 2026 14:27:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=48336583</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=48336583</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48336583</guid></item><item><title><![CDATA[New comment by azuanrb in "The last six months in LLMs in five minutes"]]></title><description><![CDATA[
<p>It depends on what you’re comparing it against. For $20, OpenAI is still probably the best value for SOTA models. In terms of limits, you can use GPT-5.4 instead of 5.5. The intelligence feels similar, but it’s cheaper. You can also experiment with other harnesses like pi. It’s lightweight but capable enough, and its token usage is definitely much more efficient.</p>
]]></description><pubDate>Tue, 19 May 2026 07:58:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48190510</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=48190510</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48190510</guid></item><item><title><![CDATA[New comment by azuanrb in "No More JetBrains Products for Me"]]></title><description><![CDATA[
<p>> Granted, I tend to run older hardware, but it seems that most other programs on my machine run fast and happy<p>Curious what hardware you’re on. I’m in the same camp with JetBrains products, performance has always been my biggest complaint. Apple M chips made a huge difference though. It’s still not my preference, but at least it’s a lot more usable now. Most of my colleagues run multiple instances daily without issues.</p>
]]></description><pubDate>Mon, 18 May 2026 21:06:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=48185621</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=48185621</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48185621</guid></item><item><title><![CDATA[New comment by azuanrb in "I am worried about Bun"]]></title><description><![CDATA[
<p>If I had to guess, it comes down to speed of iteration. Claude Code is built on JavaScript, so Bun aligns well with their current stack.<p>Switching to Go or Rust would only make sense if performance were the main priority, which doesn’t seem to be the case. Their current setup lets them ship quickly. A rewrite in Go would likely slow that down.<p>Codex moved to Rust, and you can see the trade-off. Performance improved, but release velocity dropped. They’re also still catching up to Claude Code, so they don’t face the same pressure to ship as fast.</p>
]]></description><pubDate>Mon, 04 May 2026 18:49:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=48013149</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=48013149</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48013149</guid></item><item><title><![CDATA[New comment by azuanrb in "Claude Code refuses requests or charges extra if your commits mention "OpenClaw""]]></title><description><![CDATA[
<p>It's probably their system prompt. Unlike Claude Code, they don't ban you for using different harness with their subscription (for now). If you use pi, their "safety" is off. Works great for me.</p>
]]></description><pubDate>Thu, 30 Apr 2026 17:56:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47966013</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47966013</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47966013</guid></item><item><title><![CDATA[New comment by azuanrb in "DeepSeek v4"]]></title><description><![CDATA[
<p>I have $20 ChatGPT subscription. Stopped Anthropic $20 subscription since the limit ran out too fast. That's my frontier model(s).<p>For OSS model, I have z.ai yearly subscription during the promo. But it's a lot more expensive now. The model is good imo, and just need to find the right providers. There are a lot of alternatives now. Like I saw some good reviews regarding ollama cloud.</p>
]]></description><pubDate>Fri, 24 Apr 2026 08:26:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=47887317</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47887317</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47887317</guid></item><item><title><![CDATA[New comment by azuanrb in "Claude Code to be removed from Anthropic's Pro plan?"]]></title><description><![CDATA[
<p>In the end, companies are made of individuals. In my previous company, I'm one of the individual who advocate for Claude Code adoption. Amongst my circle too, most who have the authority to make an impact on the AI direction. Safe to say I no longer suggest Anthropic to anyone anymore.</p>
]]></description><pubDate>Wed, 22 Apr 2026 08:25:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=47860681</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47860681</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47860681</guid></item><item><title><![CDATA[New comment by azuanrb in "Anthropic says OpenClaw-style Claude CLI usage is allowed again"]]></title><description><![CDATA[
<p>FAANG already did this all the time isn't it? Regardless of their policy. US is no better than China from my point of view. In this case, I see no difference between sending my prompts to US or China companies. At least China models are open source.</p>
]]></description><pubDate>Tue, 21 Apr 2026 10:20:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47846863</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47846863</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47846863</guid></item><item><title><![CDATA[New comment by azuanrb in "Not buying another Kindle"]]></title><description><![CDATA[
<p>One of the last physical books I owned was The Three-Body Problem trilogy in a single volume. It was massive, heavy and honestly beautiful. I loved it.<p>Then I switched to the Kobo Libra Colour. The weight and portability make a huge difference. Having my entire library with me means I am no longer stuck with whatever I decided to bring before leaving home.<p>The color display is not amazing, but it is good enough for comics. I have been reading things like Attack on Titan and Spider-Man on it. Reading tech books has been great too, especially those with graphs and images.<p>If I had to sum it up in one word, versatile.</p>
]]></description><pubDate>Mon, 20 Apr 2026 21:12:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=47840825</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47840825</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47840825</guid></item><item><title><![CDATA[New comment by azuanrb in "Anthropic downgraded cache TTL on March 6th"]]></title><description><![CDATA[
<p>As a Pro user, even though these issues and bugs are “new,” the downgrade has been noticeable since January. I’ve unsubscribed because the Pro plan is no longer usable for me.<p>It’s only making the news now because it’s affecting Max users as well ($100/$200 plans). I understand the need for change, but having zero communication about it is just wrong.</p>
]]></description><pubDate>Sun, 12 Apr 2026 13:35:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=47739459</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47739459</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47739459</guid></item><item><title><![CDATA[New comment by azuanrb in "ChatGPT Pro now starts at $100/month"]]></title><description><![CDATA[
<p>Same for me. I'm on $20 plan for both and I use them both interchangeably. Similar "intelligence" imo. Just different way of doing things, that's all. But Claude is getting worse in terms of token usage so I've cancelled my plan last month.</p>
]]></description><pubDate>Thu, 09 Apr 2026 18:30:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47707631</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47707631</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47707631</guid></item><item><title><![CDATA[New comment by azuanrb in "GLM-5.1: Towards Long-Horizon Tasks"]]></title><description><![CDATA[
<p>Have you compared it with using Claude Code as the harness? It performs much better than opencode for me.</p>
]]></description><pubDate>Tue, 07 Apr 2026 17:22:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47678554</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47678554</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47678554</guid></item><item><title><![CDATA[New comment by azuanrb in "Tailscale's new macOS home"]]></title><description><![CDATA[
<p>I’ve been using Bartender (paid) and Thaw (free) to manage my menu bar. Recently, both apps have become quite buggy. I’m not sure whether this is due to macOS or if there are better alternatives I’m not aware of.</p>
]]></description><pubDate>Thu, 02 Apr 2026 18:52:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47618631</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47618631</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47618631</guid></item><item><title><![CDATA[New comment by azuanrb in "GPT-5.4"]]></title><description><![CDATA[
<p>5.2 to 5.3 is the big leap for coding agents, so I'd say you're already missing out quite a bit.</p>
]]></description><pubDate>Fri, 06 Mar 2026 05:43:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47271316</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47271316</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47271316</guid></item><item><title><![CDATA[New comment by azuanrb in "Setting up phones is a nightmare"]]></title><description><![CDATA[
<p>I’m not sure about the formal evidence, but to me it’s quite straightforward. I installed the official banking apps on my parents’ phones and told them to use only those apps for banking. Nothing else.<p>If they use a website, they might mistype the URL or click on a fake link. They don’t really use bookmarks either. Even if they manage to reach the correct site or add it to their home screen, they still have to log in again each time they use it. The app removes all of that—they just tap one icon. Passkeys may improve web security, but they still have a long way to go for non-technical users.<p>Notification sucks, but overall I’m still in favor of it until we have something better. I’ve had to replace my credit card a few times due to fraud cases, and the same happened to my parents. Because we get instant notifications for every transaction or authentication attempt, we know immediately if something suspicious happens. That’s not really possible with web push, especially since our banks don’t support it.<p>Authentication is much better in the app as well. In the past, banks would ask lots of personal questions over the phone, which I’m no longer comfortable answering unless I made the call myself. With the app, the account is tied to one device, and biometric login makes it easy and secure. Any approval happens inside the app, which feels safer.<p>App is definitely not perfect, but for the majority of people (non-tech), it's just a lot easier and (unfortunately) safer for them.</p>
]]></description><pubDate>Mon, 02 Mar 2026 19:25:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=47222842</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47222842</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47222842</guid></item><item><title><![CDATA[New comment by azuanrb in "Setting up phones is a nightmare"]]></title><description><![CDATA[
<p>In my country, we do. For starters, we use apps for authentication and notifications. We can debate whether web push is viable, but most banking apps simply do not rely on it. As for older people, I would rather they use an app than a website because it is far too easy to fall victim to phishing attacks, no matter how much we educate them.</p>
]]></description><pubDate>Mon, 02 Mar 2026 04:04:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=47213749</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47213749</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47213749</guid></item><item><title><![CDATA[New comment by azuanrb in "Google restricting Google AI Pro/Ultra subscribers for using OpenClaw"]]></title><description><![CDATA[
<p>I’m aware of the tweet that says otherwise, but until they update their legal documentation, it’s still not allowed.<p>> OAuth authentication (used with Free, Pro, and Max plans) is intended exclusively for Claude Code and Claude.ai. Using OAuth tokens obtained through Claude Free, Pro, or Max accounts in any other product, tool, or service — including the Agent SDK — is not permitted and constitutes a violation of the Consumer Terms of Service.<p><a href="https://code.claude.com/docs/en/legal-and-compliance#authentication-and-credential-use" rel="nofollow">https://code.claude.com/docs/en/legal-and-compliance#authent...</a></p>
]]></description><pubDate>Mon, 23 Feb 2026 04:56:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47118307</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47118307</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47118307</guid></item><item><title><![CDATA[New comment by azuanrb in "Claws are now a new layer on top of LLM agents"]]></title><description><![CDATA[
<p>When I tried it out last time, a lot of the features are macOS only. It works on other OS, but not all.</p>
]]></description><pubDate>Sat, 21 Feb 2026 14:40:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=47101257</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47101257</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47101257</guid></item><item><title><![CDATA[New comment by azuanrb in "Gemini 3.1 Pro"]]></title><description><![CDATA[
<p>The CLI needs work, or they should officially allow third-party harnesses. Right now, the CLI experience is noticeably behind other SOTA models. It actually works much better when paired with Opencode.<p>But with accounts reportedly being banned over ToS issues, similar to Claude Code, it feels risky to rely on it in a serious workflow.</p>
]]></description><pubDate>Thu, 19 Feb 2026 17:22:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47076328</link><dc:creator>azuanrb</dc:creator><comments>https://news.ycombinator.com/item?id=47076328</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47076328</guid></item></channel></rss>