<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: ggregoire</title><link>https://news.ycombinator.com/user?id=ggregoire</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 26 May 2026 20:18:19 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ggregoire" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ggregoire in "Using AI to write better code more slowly"]]></title><description><![CDATA[
<p>> On top of that, I enjoy programming, reverse engineering, etc. and I feel that the LLMs, while able to solve some problems or deliver some features, take that fun away.<p>Same, I prefer asking one or multiple very technical questions to Gemini, analyze, compare and understand the responses then implement it myself based on what I learned (or just integrate it to the codebase as it is, if I asked it to write a function) than delegating away all the fun to an agent.</p>
]]></description><pubDate>Tue, 26 May 2026 14:44:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=48280567</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=48280567</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48280567</guid></item><item><title><![CDATA[New comment by ggregoire in "Stanford report highlights growing disconnect between AI insiders and everyone"]]></title><description><![CDATA[
<p>> but the enthusiasm on the ground is lacking<p>Using claude and friends takes all the fun out of the job, so I'm not surprised engineers are not enthusiastic. It's cool for 1 month then you realize we went from solving problems and implementing algos and optimizing slow code and fixing security issues and other fun stuff, to writing prompts all day long.</p>
]]></description><pubDate>Mon, 13 Apr 2026 22:44:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758903</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47758903</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758903</guid></item><item><title><![CDATA[New comment by ggregoire in "The economics of software teams: Why most engineering orgs are flying blind"]]></title><description><![CDATA[
<p>Also, it's obviously faster to copy Slack 1-to-1 than inventing it from scratch. Making Slack was not just coding.</p>
]]></description><pubDate>Mon, 13 Apr 2026 14:08:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=47752211</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47752211</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47752211</guid></item><item><title><![CDATA[New comment by ggregoire in "JSON formatter Chrome plugin now closed and injecting adware"]]></title><description><![CDATA[
<p>It's quite remarkable that a chrome extension can just update overnight and start injecting adware (or worse) and not a single warning from chrome. I shouldn't have to read hackernews to find out.</p>
]]></description><pubDate>Sat, 11 Apr 2026 01:54:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=47726466</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47726466</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47726466</guid></item><item><title><![CDATA[New comment by ggregoire in "Ask HN: Any interesting niche hobbies?"]]></title><description><![CDATA[
<p>I've been playing exclusively CRPGs for the last 12 months or so, which was kinda a niche genre before the success of BG3. There are tons of way to beat those games and optimizing how you build your party and characters (what players call "min-maxing") while following a highly narrative story is a lot of fun. Most of them are quite old and often on sales for like 5 bucks on Steam, for which you get hundreds of hours of gameplay. A few recommendations: Obsidian's Pillars of Eternity 1 & 2, Owlcat's Pathfinders & W40K Rogue Trader, Larian's Divinity 1, 2 & BG3, Bioware's BG1 & BG2, etc…</p>
]]></description><pubDate>Wed, 08 Apr 2026 17:47:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=47693726</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47693726</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47693726</guid></item><item><title><![CDATA[New comment by ggregoire in "Sam Altman may control our future – can he be trusted?"]]></title><description><![CDATA[
<p>> The difference isn't that the average techie doesn't dream of making a billion by any means necessary<p>That's actually the difference, most people don't want a billion</p>
]]></description><pubDate>Tue, 07 Apr 2026 01:44:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47669753</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47669753</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47669753</guid></item><item><title><![CDATA[New comment by ggregoire in "Claude Code Unpacked : A visual guide"]]></title><description><![CDATA[
<p>Any loser is a "full stack software engineer" nowadays thanks to claude.</p>
]]></description><pubDate>Wed, 01 Apr 2026 16:45:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=47603309</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47603309</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47603309</guid></item><item><title><![CDATA[New comment by ggregoire in "Claude Code Unpacked : A visual guide"]]></title><description><![CDATA[
<p>That's a bit dishonest, the consensus on HN seems to be that LLMs are very good at oneshotting small projects from scratch. Especially when using super mainstream technologies like html and tailwind, as does the discussed website. And especially when it's a one time operation and the project will never need to be maintained, like the discussed website.</p>
]]></description><pubDate>Wed, 01 Apr 2026 16:08:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47602746</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47602746</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47602746</guid></item><item><title><![CDATA[New comment by ggregoire in "Slop is not necessarily the future"]]></title><description><![CDATA[
<p>3. Coding is fun, prompting not so much</p>
]]></description><pubDate>Tue, 31 Mar 2026 20:03:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47592704</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47592704</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47592704</guid></item><item><title><![CDATA[New comment by ggregoire in "How to run Qwen 3.5 locally"]]></title><description><![CDATA[
<p>> I find Qwen useless for anything but coding tasks because if its insufferable sycophancy<p>We use Qwen at work since 2.0 for text/image/video analysis (summarization, categorization, NER, etc), I think it's impressive. We ask for JSON and always ask "do not explain your response".</p>
]]></description><pubDate>Sun, 08 Mar 2026 14:11:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47297472</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47297472</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47297472</guid></item><item><title><![CDATA[New comment by ggregoire in "How will OpenAI compete?"]]></title><description><![CDATA[
<p>> the moat of 'users won't be arsed to download a different app'???<p>don't even need to download anything, just open your browser and go to google.com to use gemini<p>last week-end, I've seen a non-tech friend who previously used chatGPT on his phone, just go on google to ask stuff to the AI (they have no idea it's gemini and it doesn't matter)<p>if you are not looking for having some kind of relationship with an AI (from what I understand people use chatGPT for this use case), but just looking for an AI to search stuff, then in my opinion you can't beat google search + gemini summary all at once for free with a single prompt</p>
]]></description><pubDate>Thu, 26 Feb 2026 18:00:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47169611</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47169611</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47169611</guid></item><item><title><![CDATA[New comment by ggregoire in "Stripe valued at $159B, 2025 annual letter"]]></title><description><![CDATA[
<p>in 2 hours with claude code</p>
]]></description><pubDate>Tue, 24 Feb 2026 18:19:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=47140585</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47140585</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47140585</guid></item><item><title><![CDATA[New comment by ggregoire in "We're no longer attracting top talent: the brain drain killing American science"]]></title><description><![CDATA[
<p>> I don’t think people all over Europe/Asia/Africa migrate to China.<p>Learning mandarin is the major blocker imo, more people would move if the language was easier.</p>
]]></description><pubDate>Fri, 20 Feb 2026 00:18:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=47081859</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47081859</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47081859</guid></item><item><title><![CDATA[New comment by ggregoire in "Gemini 3.1 Pro"]]></title><description><![CDATA[
<p>I use it in Google Search. For example yesterday I typed in Google "postgres generate series 24 hour" and this morning "ffmpeg convert mp4 to wav". Previously I would have clicked on the first StackOverflow result (RIP), now I just take it from the Gemini summary (I'd say 95% of the time it's correct for basic programming language questions. I remember some hallucinations about psycopg3 and date-fns tho. As usual with AI, you need to already know the answer, at least partially, to detect the bs).<p>Also what's great about Gemini in Google Search is that the answer comes with several links, I use them sometimes to validate the correctness of the solution, or check how old the solution is (I've never used chatGPT so I don't know if chatGPT does it).</p>
]]></description><pubDate>Thu, 19 Feb 2026 18:51:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47077519</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47077519</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47077519</guid></item><item><title><![CDATA[New comment by ggregoire in "AI is destroying open source, and it's not even good yet"]]></title><description><![CDATA[
<p>> StackOverflow was well on its way to death even without ChatGPT, just look at the graph from [0]. It has been in steady consistent decline since 2014.<p>> [0] <a href="https://blog.pragmaticengineer.com/stack-overflow-is-almost-dead" rel="nofollow">https://blog.pragmaticengineer.com/stack-overflow-is-almost-...</a> (monthly question asked on Stack Overflow)<p>"monthly questions asked" is a weird metric to measure the decline of StackOverflow tho. How many times are people gonna ask how to compare 2 dates in python, or how to efficiently iterate an array in javascript? According to the duplicates rule on SO, should be once anyway. So it's just inevitable that "monthly questions asked" will forever decrease after reaching its peak, since everything has already been asked. Didn't mean it was dead tho, people still needed to visit the site to read the responses.<p>A better metric to measure its decline would be "monthly visits", which I guess was still pretty high pre LLM (100s of millions per month?), even if the "monthly questions asked" was declining. But now I imagine their "monthly visits" is closer to zero than 1M. I mean, even if you don't use Claude and its friends, searching anything about programming on Google returns a Gemini answer that probably comes from StackOverflow, removing any reason to ever visit the site…</p>
]]></description><pubDate>Tue, 17 Feb 2026 19:10:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47051662</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47051662</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47051662</guid></item><item><title><![CDATA[New comment by ggregoire in "Modern CSS Code Snippets: Stop writing CSS like it's 2015"]]></title><description><![CDATA[
<p>Yes we agree, my comment was for tailwind users. :) I was replying to you because you gave the example of a Button component, and it's a good example to demonstrate that you don't need tailwind to style components.</p>
]]></description><pubDate>Mon, 16 Feb 2026 20:36:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47039995</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47039995</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47039995</guid></item><item><title><![CDATA[New comment by ggregoire in "Modern CSS Code Snippets: Stop writing CSS like it's 2015"]]></title><description><![CDATA[
<p>> If everything in your code is a React component, I get why you would just want to write the styles right there.<p>Even for keeping the style close to the component, you can just use standard css.<p>Create a folder Button, create two files Button.tsx and Button.css in that folder, import the css file in the tsx file, add a class "button" on the first element the tsx file renders, start all the rules in the css file with ".button " to encapsulate the style.<p>People will say it's too much work, but it took me like 5 sec.</p>
]]></description><pubDate>Mon, 16 Feb 2026 20:03:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=47039577</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47039577</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47039577</guid></item><item><title><![CDATA[New comment by ggregoire in "Fix the iOS keyboard before the timer hits zero or I'm switching back to Android"]]></title><description><![CDATA[
<p>What infuriates me the most is iOS being absolutely unable to detect which language I'm currently writing in and automatically replacing words in one language to another. I write in 3 languages on a daily basis and it's making iOS totally lose its mind. For instance I'm 5 words deep into a message in French with a person I'm only speaking French with, and somehow iOS still thinks I'm making typos every other word and automatically replaces them with English or Spanish words.<p>And it wouldn't be so bad if moving the cursor at the end of a word or selecting a few letters in a word or even selecting an entire word wasn't nearly impossible on iOS (and I have relatively small fingers… I have no idea how people with big hands can do that stuff). Writing a 10 words messages can take me like 2 minutes sometimes because of all the errors made by iOS that I need to manually fix, and having to retry like 5 times to position the cursor successfully at the end of every word I need to rewrite in the correct language…</p>
]]></description><pubDate>Fri, 13 Feb 2026 19:49:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=47006907</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=47006907</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47006907</guid></item><item><title><![CDATA[New comment by ggregoire in "Gemini 3 Deep Think"]]></title><description><![CDATA[
<p>Do we know what model is used by Google Search to generate the AI summary?<p>I've noticed this week the AI summary now has a loader "Thinking…" (no idea if it was already there a few weeks ago). And after "Thinking…" it says "Searching…" and shows a list of favicons of popular websites (I guess it's generating the list of links on the right side of the AI summary?).</p>
]]></description><pubDate>Fri, 13 Feb 2026 01:49:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=46997952</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=46997952</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46997952</guid></item><item><title><![CDATA[New comment by ggregoire in "Coding agents have replaced every framework I used"]]></title><description><![CDATA[
<p>> How much you like coding. If you like coding then using AI is less fun.<p>I'm surprised this is never brought up here on "Hacker" News. I've been reading HN for 14 years and all this time I thought people here enjoyed programming. Turns out the majority hates it apparently.</p>
]]></description><pubDate>Sun, 08 Feb 2026 00:28:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46929938</link><dc:creator>ggregoire</dc:creator><comments>https://news.ycombinator.com/item?id=46929938</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46929938</guid></item></channel></rss>