<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: foo42</title><link>https://news.ycombinator.com/user?id=foo42</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 17 Apr 2026 09:55:39 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=foo42" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by foo42 in "Sometimes powerful people just do dumb shit"]]></title><description><![CDATA[
<p>I suspect sycophancy has a lot to do with things . People with power attract those who want their favour and/or money who will align themselves to please the powerful rather than steer them to their best selves. Furthermore as the sycophants accumulate the genuine voices likely begin to sound out of place, like their _against_ the individual. Ironically paranoia gets deployed in the wrong direction to push out the true voices.<p>I worry this fate will become more common. Everyone can hit up an artificial sycophant at will who they've been told is super intelligent and yet claims their ideas are full of deep insight.</p>
]]></description><pubDate>Tue, 14 Apr 2026 07:18:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47762323</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47762323</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47762323</guid></item><item><title><![CDATA[New comment by foo42 in "LLM Wiki – example of an "idea file""]]></title><description><![CDATA[
<p>I built a very similar system into my own assistant type project. In all honesty though I've not used it enough to know how well it works out in practice.</p>
]]></description><pubDate>Sun, 05 Apr 2026 07:30:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47647045</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47647045</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47647045</guid></item><item><title><![CDATA[New comment by foo42 in "POSSE – Publish on your Own Site, Syndicate Elsewhere"]]></title><description><![CDATA[
<p>I've never implemented it, but I think WebMentions was supposed to enable this</p>
]]></description><pubDate>Mon, 23 Mar 2026 11:06:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47487775</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47487775</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47487775</guid></item><item><title><![CDATA[New comment by foo42 in "Kagi: Small Web Just Got Bigger"]]></title><description><![CDATA[
<p>Since Kagi small web was on HN a few days ago I've been visiting multiple times a day and spelunking around. I've added a number of interesting feeds to my RSS reader off the back of it already.</p>
]]></description><pubDate>Sun, 22 Mar 2026 19:23:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47481105</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47481105</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47481105</guid></item><item><title><![CDATA[New comment by foo42 in "Astral to Join OpenAI"]]></title><description><![CDATA[
<p>I was looking into Fedify just yesterday! I'm trying to decide whether to A) try and make my blog an activity pub instance of some sort, B) host my own Mastodon instance, or C) Use someone else's Mastodon server and link to my blog POSSE style. If I go with option A (which somehow feels like how things are _supposed_ to work) Fedify looks like the way to make it happen.<p>Thanks for your work.</p>
]]></description><pubDate>Fri, 20 Mar 2026 08:27:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47451945</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47451945</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47451945</guid></item><item><title><![CDATA[New comment by foo42 in "Show HN: Three new Kitten TTS models – smallest less than 25MB"]]></title><description><![CDATA[
<p>minor nit to pick: Welsh accents are British accents as Wales is in Britain. In fact by some definitions it's the most British part.<p>People from outside the UK often use British as synonymous with English, and in the context of accents, often a South East English accent or some sort of Received Pronunciation (RP) accent. Technically a "British" accent could be from anywhere in England, Scotland, or Wales, and therefore by extension might not even be the English language.<p>While I'm here, since it's generally confusing, the UK is Great Britain and Northern Ireland. Great Britain is England, Scotland, and Wales.</p>
]]></description><pubDate>Fri, 20 Mar 2026 08:13:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=47451836</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47451836</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47451836</guid></item><item><title><![CDATA[New comment by foo42 in "Wander – A tiny, decentralised tool to explore the small web"]]></title><description><![CDATA[
<p>I feel like activity pub was supposed to / does enable this.<p>Perhaps someone better informed than I could comment.</p>
]]></description><pubDate>Thu, 19 Mar 2026 11:58:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47437853</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47437853</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47437853</guid></item><item><title><![CDATA[New comment by foo42 in "Many SWE-bench-Passing PRs would not be merged"]]></title><description><![CDATA[
<p>Yeah I've been wondering if the increasing coding RL is going to draw models towards very short term goals relative to just learning from open source code in the wild</p>
]]></description><pubDate>Thu, 12 Mar 2026 11:04:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=47349037</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47349037</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47349037</guid></item><item><title><![CDATA[New comment by foo42 in "Agents that run while I sleep"]]></title><description><![CDATA[
<p>I've been thinking about this recently and it seems like the most enthusiastic boosters always suggest difference in results is a skill issue, but I feel like there are 4 factors which multiply out to influence how much value someone gets:
- The quality of model output for _your particular domain / tech stack_. Models will always do better with languages and libraries they see a lot of than esoteric or proprietary
- The degree to which "works" = "good" in your scenario. For a one off script, "works" is all that matters, for a long lived core library, there are other considerations.
- The degree to which "works" can be easily (best yet, automatically) verified.
- Techniques, existing code cleanliness, documentation etc.<p>Boosters tend to lay all different experiences at the feet of this last, yet I'd argue the others are equally significant.<p>On the other hand, if you want to get the best results you can given the first 3 (which are generally out of one's control) then don't presume there's nothing you can do to improve the 4th.</p>
]]></description><pubDate>Wed, 11 Mar 2026 08:56:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47333196</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47333196</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47333196</guid></item><item><title><![CDATA[New comment by foo42 in "Agents that run while I sleep"]]></title><description><![CDATA[
<p>I salaried employees who are paid by time, and are paying their own Anthropic bills.<p>Initially there is perhaps a mitigating advantage of briefly impressing ourselves or others with output, but that will quickly fade into the new normal.<p>Net result: employee paying significant money to produce more, but capturing none of that value.</p>
]]></description><pubDate>Wed, 11 Mar 2026 08:40:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=47333080</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47333080</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47333080</guid></item><item><title><![CDATA[New comment by foo42 in "Claude Code, Claude Cowork and Codex #5"]]></title><description><![CDATA[
<p>> And this is the best country in the world, with the best system of government, because private citizens can voice their disagreement with such actions, including by refusal to participate.<p>On the off chance other Americans were unaware of this: Other countries are democracies too (and many are better functioning)</p>
]]></description><pubDate>Tue, 10 Mar 2026 07:16:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47320013</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47320013</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47320013</guid></item><item><title><![CDATA[New comment by foo42 in "Ask HN: What Are You Working On? (March 2026)"]]></title><description><![CDATA[
<p>Sounds fun. Can't beat a good whimsical project!</p>
]]></description><pubDate>Mon, 09 Mar 2026 08:03:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=47306053</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47306053</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47306053</guid></item><item><title><![CDATA[New comment by foo42 in "The Eternal Promise: A History of Attempts to Eliminate Programmers"]]></title><description><![CDATA[
<p>I've been wondering recently if there's some practical path forward for some sort of co-op based LLM training. Something which puts the power in the hands of the users somehow.</p>
]]></description><pubDate>Sat, 28 Feb 2026 20:51:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47200086</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47200086</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47200086</guid></item><item><title><![CDATA[New comment by foo42 in "How will OpenAI compete?"]]></title><description><![CDATA[
<p>while we're talking pronunciation I'm on an (entirely pointless) one man mission to have "lemon" stick as a pronunciation of "LLM".</p>
]]></description><pubDate>Thu, 26 Feb 2026 08:11:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47163312</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47163312</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47163312</guid></item><item><title><![CDATA[New comment by foo42 in "How will OpenAI compete?"]]></title><description><![CDATA[
<p>The only two models I ever hear non technical people mention are ChatGPT and occasionally Gemini</p>
]]></description><pubDate>Thu, 26 Feb 2026 07:58:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47163218</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47163218</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47163218</guid></item><item><title><![CDATA[New comment by foo42 in "How will OpenAI compete?"]]></title><description><![CDATA[
<p>I hope you're right, but is there any guarantee that there will continue to be institutions willing to spend the money to produce open models?<p>I almost wonder if we need some sort of co-op for training and another for hosted inference</p>
]]></description><pubDate>Thu, 26 Feb 2026 07:55:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47163188</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47163188</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47163188</guid></item><item><title><![CDATA[New comment by foo42 in "NanoClaw moved from Apple Containers to Docker"]]></title><description><![CDATA[
<p>I've been taking a similar approach with my own exploration.</p>
]]></description><pubDate>Tue, 24 Feb 2026 18:01:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47140339</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47140339</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47140339</guid></item><item><title><![CDATA[New comment by foo42 in "Why I don't think AGI is imminent"]]></title><description><![CDATA[
<p>I worry that if the reality lives up to investors dreams it will be massively disruptive for society which will lead us down dark paths. On the other hand if it _doesn't_ live up to their dreams, then there is so much invested in that dream financially that it will lead to massive societal disruption when the public is left holding the bag, which will also lead us down dark paths.</p>
]]></description><pubDate>Mon, 16 Feb 2026 09:17:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=47032763</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47032763</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47032763</guid></item><item><title><![CDATA[New comment by foo42 in "Building SQLite with a small swarm"]]></title><description><![CDATA[
<p>I agree.<p>While I'm generally sympathetic to the idea that humans and LLM creativity is broadly similar (combining ideas absorbed elsewhere in new ways), when we ask for something that already exists it's basically just laundering open source code</p>
]]></description><pubDate>Mon, 16 Feb 2026 08:35:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47032458</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=47032458</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47032458</guid></item><item><title><![CDATA[New comment by foo42 in "Using an engineering notebook"]]></title><description><![CDATA[
<p>Same for me. I also make extensive use of adding links to anything relevant. Spent a bunch of time discussing something in a slack thread: link it. Read some documentation: link it. Had a chat with an llm in a chat window: link it. Writing notes about how a bunch of code works : link to the functions. For this last one I've registered a custom vim:// URL scheme on my system which lets me link to a symbol within a given file, and when clicked focuses the relevant tmux window and navigates the relevant vim instance (using named pipes) to the symbol, or opens a fresh one if not already open.</p>
]]></description><pubDate>Thu, 12 Feb 2026 09:10:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=46986522</link><dc:creator>foo42</dc:creator><comments>https://news.ycombinator.com/item?id=46986522</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46986522</guid></item></channel></rss>