<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: dgunay</title><link>https://news.ycombinator.com/user?id=dgunay</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 05:20:26 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dgunay" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dgunay in "AI usage generates a fragile codebase"]]></title><description><![CDATA[
<p>This isn't uncommon in the gaming industry, or at least, I'd assume it isn't based on how many game executables and debugging tlm/logs appear to bear the name of a working title or codename instead of the game's actual release title.</p>
]]></description><pubDate>Tue, 10 Nov 2026 20:53:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=50446183</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50446183</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50446183</guid></item><item><title><![CDATA[New comment by dgunay in "Ask HN: What are you working on? (November 2026)"]]></title><description><![CDATA[
<p>My maternal grandmother compiled a genealogy of our family in the 90s, going back to the 1600s. This year my paternal grandmother passed away, and as I was going through her old photos it just sort of hit me that none of my relatives seemed the sort to want to carry on the work that my maternal grandma did. The computer my grandma used to author the book is AFAIK lost, so I also didn't want the genealogy to be lost forever if we lose the physical copies, so I took my copy and digitized it.<p>I first scanned all ~280 pages with the Google Drive mobile app document scanner. I fed that into Claude and asked it to begin a transcription effort. It launched a swarm of subagents to transcribe as much of it as it could, going back to me to retake bad images and clarify illegible text. Once I had it fully transcribed, I had it create a digital PDF version of the book, an mdbook site, a GEDCOM export, and now I'm having it build a website to interactively browse the family tree. Along the way I've gone back and had it clean up transcription or formatting errors.<p>I plan on extending it with what I know and by asking my family and my wife's side of the family for more information.</p>
]]></description><pubDate>Tue, 10 Nov 2026 08:15:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=50437466</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50437466</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50437466</guid></item><item><title><![CDATA[New comment by dgunay in "Claude Fable 5.2 and Mythos 5.2"]]></title><description><![CDATA[
<p>If you understand your problem well and know 80-90% what you want it to look like (or it just isn't very hard), it's just more cost effective to use a smaller model. Even Opus is overkill for a lot of the work I do. Most code I produce is from Luna Max implementing against fairly prescriptive plans made by bigger models.</p>
]]></description><pubDate>Mon, 09 Nov 2026 20:22:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=50431440</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50431440</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50431440</guid></item><item><title><![CDATA[New comment by dgunay in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>I use AI primarily through work, I don't pay for a personal AI sub.<p>I do have some OpenRouter credits but I mostly use them sparingly to try open weight models out for small personal projects.<p>I currently interact primarily with Claude Code, but most of my async workers are on Codex.<p>The orchestration part is custom. I talk to a "chief of staff" Opus instance to ingest various workstreams (Jira tickets, alerts, personal ideas, etc) and turn them into beads. It launches workers to tackle individual beads using Remuda, an agent launcher I wrote at work in 2025 and open sourced earlier this year: <a href="https://github.com/yendo-eng/remuda" rel="nofollow">https://github.com/yendo-eng/remuda</a>. I configure profiles in Remuda that launch containerized agents using my preferred harness and model. I update these profiles as the pareto frontier shifts. Currently it's GPT 6 Luna max for most tasks.<p>It monitors the workers and has them go through at least one round of agentic code review. It surfaces PRs for me to read once they've passed agent review. It then either ships them or hands them off to my coworkers for codebases where I'm not allowed to just merge PRs.<p>Around this workflow I had it write a small collection of skills and scripts to grease the wheels and make repetitive actions more reliable.<p>Since Remuda supports several terminal multiplexers, I've swapped out the backend 3 times: tmux -> herdr-tui -> herdr-core. There's experimental support for Rex but I'm waiting for it to mature a bit before I try and daily drive it.<p>It's not nearly as polished as some of the software factory setups and fancy GUI orchestrators I'm seeing, but it's light, hackable, and so far the bitter lesson has kept this working really well for me so I haven't felt much of a need to try anything else.<p>I have been trying out Muse for a while but it hasn't found a solid place in my life yet. Still too unreliable and too many privacy concerns to justify giving it a lot of access.</p>
]]></description><pubDate>Thu, 05 Nov 2026 05:02:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=50375407</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50375407</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50375407</guid></item><item><title><![CDATA[New comment by dgunay in "Guerrilla bike lanes: San Francisco makes illicit infrastructure permanent (2016)"]]></title><description><![CDATA[
<p>Since bikes/scooters are much faster than pedestrians, it causes problems like this when they use pedestrian infra. For an example, I was driving up to a yield-to-peds xwalk a while ago, and on the sidewalk there was a scooter going at full clip. I slowed down because I had a hunch he would do this, but he took a hard 90 deg turn at the xwalk and went straight through at speed. If I hadn't done that, I might have run him over. A pedestrian could never have done that.<p>Something similar to this dynamic happens anywhere you would "look both ways" as a driver but don't have far enough visibility to extrapolate a safe window of passage relative to the speed of oncoming traffic. It can happen when parked cars block your view of oncoming traffic, or when parked cars block view of the bike lane, or when parked cars, trees, hedges, fences etc block view of the sidewalk that a non-pedestrian is using.</p>
]]></description><pubDate>Wed, 04 Nov 2026 19:53:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=50370636</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50370636</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50370636</guid></item><item><title><![CDATA[New comment by dgunay in "Guerrilla bike lanes: San Francisco makes illicit infrastructure permanent (2016)"]]></title><description><![CDATA[
<p>In the Piers Anthony novel "On a Pale Horse", the protagonist is taught a lesson about empathy and perspective by being forced to experience the same scenario as a pedestrian, a bicyclist, and a driver.<p>Reading your comment and many others makes me think that the most "intractable" problem with shared transportation infrastructure isn't making it physically safe, it's getting people to treat other road users as human. Even a car-only road still has this problem.</p>
]]></description><pubDate>Wed, 04 Nov 2026 19:48:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=50370590</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50370590</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50370590</guid></item><item><title><![CDATA[New comment by dgunay in "Local Wikipedia: Wikipedia, but only for things a half hour walk from you"]]></title><description><![CDATA[
<p>Definitely. I read a few articles top to bottom that I normally wouldn't have even bothered to look up on real Wikipedia, learned some cool local lore.</p>
]]></description><pubDate>Fri, 23 Oct 2026 18:48:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=50213633</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50213633</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50213633</guid></item><item><title><![CDATA[New comment by dgunay in "Claude Duet"]]></title><description><![CDATA[
<p>I use Muse. So far the biggest value to me is 1) being a more "squishy" reminder service than a typical task tracker, because it can at its own discretion raise stuff to my attention and 2) attempting things that I normally wouldn't have the energy to do on my own. It doesn't always succeed, but a 50/50 chance of it even getting done is still an improvement in my book. Things like 311-ing small problems I see on walks, grabbing free games from EGS, etc.</p>
]]></description><pubDate>Wed, 21 Oct 2026 23:38:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=50189151</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50189151</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50189151</guid></item><item><title><![CDATA[New comment by dgunay in "Meta ordered to pay $25B penalty in New Mexico Cambridge Analytica case"]]></title><description><![CDATA[
<p>Maybe the $25B isn't guaranteed and doesn't seriously harm them on its own, but if the legal landscape shifts enough to make fines of this scale more common than the usual dozens-to-hundreds of millions, then it starts to impact their bottom line.</p>
]]></description><pubDate>Wed, 21 Oct 2026 22:04:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=50188304</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50188304</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50188304</guid></item><item><title><![CDATA[New comment by dgunay in "Way to Play Super Mario 64: On Apple Vision Pro"]]></title><description><![CDATA[
<p>They're very different games. I'd play 64 first simply because it's a landmark in gaming history, but Paper Mario is one of my favorite games ever.</p>
]]></description><pubDate>Wed, 21 Oct 2026 18:59:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=50185847</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50185847</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50185847</guid></item><item><title><![CDATA[New comment by dgunay in "Steam Users Beg for "No AI" Filter as Vibecoders Flood Next Fest"]]></title><description><![CDATA[
<p>It may not, by some philosophical definition, but most consumers (and I'd say most programmers too) place little importance on code as a human artistic expression. In the case of games the art assets are also a much more clear and direct signal that there was AI involved in the creation of the game. A game with handmade art but vibe coded game logic might not be as obvious.</p>
]]></description><pubDate>Tue, 20 Oct 2026 17:56:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=50170126</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50170126</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50170126</guid></item><item><title><![CDATA[New comment by dgunay in "Ukraine claims first drone evacuation of wounded soldier"]]></title><description><![CDATA[
<p>Doesn't this have potential applications in disaster relief?</p>
]]></description><pubDate>Mon, 19 Oct 2026 18:32:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=50156099</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50156099</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50156099</guid></item><item><title><![CDATA[New comment by dgunay in "Tesla Roadster"]]></title><description><![CDATA[
<p>I feel like a curmudgeon because like yes the demo was really cool, but more from the standpoint that they were willing to do a stunt like that in an industry that is incredibly boring (at least in the US). The engineering behind making a relatively heavy object fly around with thrusters is very well understood at this point, I wouldn't call it "incredible" to rig RCS thrusters on a brick and make it do a barrel roll.<p>EDIT: I want to make it clear that 1) I'm not talking about the driving upside down thing, and 2) just because I am not sensationalizing the kickflip trick as some incredibly complex endeavor doesn't mean I didn't think it was cool and I'm some kind of hollow, depressed sad sack. The kick flip made me laugh my ass off, but be real. His companies make rockets that can belly flop and land themselves, stream hi res video of reentry using LEO satellite constellations, catch huge boosters in towers, and this is what's blowing your mind?</p>
]]></description><pubDate>Fri, 16 Oct 2026 22:10:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=50125434</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50125434</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50125434</guid></item><item><title><![CDATA[New comment by dgunay in "Do dentists know what they're doing?"]]></title><description><![CDATA[
<p>I briefly shadowed a doctor when I was interested in potentially going to medical school. I sat down while he met with a patient. He left the room pretty quickly. From the conversation I figured he'd be right back and just went to get something or check something. He comes back in 5 minutes later and I find out that he'd gotten up and seen 3-4 other patients before realizing I was still in the first room.</p>
]]></description><pubDate>Wed, 14 Oct 2026 19:25:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=50093554</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50093554</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50093554</guid></item><item><title><![CDATA[New comment by dgunay in "Show HN: XY Music Notation"]]></title><description><![CDATA[
<p>Some parts of it are not super orthogonal. Intervals aren't visually consistent, for example (E -> F vs C -> C#).<p>Having to read notes that are up in the ledger lines outside the clef kind of sucks. You just have fewer visual landmarks to hang off of.<p>This is partly a consequence of the physical instruments we have and their natural ranges, but clefs as a general concept are annoying to deal with when you have to juggle them constantly.<p>IMO it doesn't do a good job of communicating dynamics and expression. The notation used is vague (accelerando... okay how much faster, over how many measures, etc).<p>Maybe I'm holding it wrong, but recently I transcribed some of my friend's songs and managing repeats that don't neatly fit into a rigid song structure is difficult without writing very "WET" music that takes up a lot of space.<p>In a more meta sense, most sheet music is garbage. There is no inherent pit of success when it comes to creating sheet music, and writing a very good, readable score is something only well-trained musicians and composers can do. Look at free sheet music or read notation written by amateurs, you'll see missing key signatures, misspelled chords, etc. Sheet music doesn't make any concessions for people who understand music as sound first, you have to adhere to tradition and theory to produce good sheet music. Lots of musicians with decent ears cannot do this.<p>IDK, this is me trying very hard to come up with reasons to hate on sheet music.</p>
]]></description><pubDate>Wed, 14 Oct 2026 07:40:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=50083852</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50083852</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50083852</guid></item><item><title><![CDATA[New comment by dgunay in "Ask HN: How do you review code nowadays?"]]></title><description><![CDATA[
<p>We still do code review but it does bottleneck how much we can ship.<p>I'm looking at what we can do to alleviate this. Here's what I think the near future may look like, as far as getting more value per time spent out of human code review. I'm coming at this from the POV of an org that still mandates human code review and I think a lot of this advice doesn't hold if you are all-in on the black box software factory approach.<p>If you're reviewing code you're responsible for, your job now is to provide stewardship of its long term technical direction even if you are not personally reading and writing every line of code. This means preserving the coherence of designs past and present, and ensuring that they are not being worked around in service of a short-term goal.<p>Stop reading every line of every file to look for minor gotchas. Focus on core business logic and whether invariants are modeled well & to the fullest extent possible by the type system. Agents are better than most humans now at spotting insane gotchas. At least one frontier model should review most PRs.<p>In the before times, you could argue that TODO comments and small nits on PRs should be addressed, because most likely they'd never get attention again once the PR merges. Now, small issues should instead be automatically recorded and followed up on quickly by another agent. Minor code quality issues should become rules, and old code should be constantly revisited by agents to bring it up to par with new code.<p>Provide the transcripts of the session with the PR. Look for evidence of thoughtful direction & solid premise behind the conversation that led to the PR being made. In addition to providing more mentorship opportunities to the author, this also discourages meat proxying/low-value-added uses of AI. Asking someone to rewrite or completely discard a PR that's just a bad idea should no longer be the ego bruising event it once was (at least with respect to the cost sunk to make the PR).<p>Require a higher bar for proving that code works and stays working. The testing pyramid IMO should now be more of a testing hourglass. Or an upside-down pyramid, even. Automated E2E tests should be abundant. Every feature should receive adequate manual testing by an agent, with proof of work.<p>In the vein of "stays working," look for good observability and guardrails around a feature. If you're doing a good job of leveraging agents to keep code up to par, this means adding (and cycling out) feature flags, ensuring that there's adequate logging, having a cohesive monitoring solution with good coverage, and a plan for what to do if there's an issue in prod.</p>
]]></description><pubDate>Wed, 14 Oct 2026 01:34:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=50081311</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50081311</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50081311</guid></item><item><title><![CDATA[New comment by dgunay in "Gemini 4 Argon"]]></title><description><![CDATA[
<p>Gemini Flash is very dumb and gimped. Recent experience:<p>1. I ask it to list out all my old Keep notes that are just throwaway task lists, reminders, etc. to propose deleting them.<p>2. It comes up with like 4 of them (I know for a fact there are dozens, if not hundreds). I ask it for an exhaustive list.<p>3. I see its thinking trace briefly show "Refusing to produce an exhaustive list..." and then it says "Yes, that is all of them."<p>Not sure whether it's lack of intelligence, bad tools, or both, but that was extremely frustrating to see.</p>
]]></description><pubDate>Tue, 13 Oct 2026 19:07:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=50076967</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=50076967</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50076967</guid></item><item><title><![CDATA[New comment by dgunay in "AnyPS5: Port PS5 binaries to PC without emulation (87% system libraries mapped)"]]></title><description><![CDATA[
<p>Piracy is a service problem! If they release a good PC port, I will buy it, as I have done for nearly every other Rockstar game. Hell, if they were to even just automate the port using a similar tool, I wouldn't really mind if the end result were indistinguishable from a decent PC port. I just really don't want to buy a PS5 for a couple exclusives.</p>
]]></description><pubDate>Wed, 07 Oct 2026 02:02:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=49987077</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=49987077</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49987077</guid></item><item><title><![CDATA[New comment by dgunay in "Japan moves to tighten rules for foreigners"]]></title><description><![CDATA[
<p>Don't worry, I'm sure they're going to aggressively tackle the cultural and economic problems contributing to their fertility crisis, right? Right?</p>
]]></description><pubDate>Sun, 27 Sep 2026 00:40:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=49862084</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=49862084</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49862084</guid></item><item><title><![CDATA[New comment by dgunay in "Why is the liver so weirdly regenerative?"]]></title><description><![CDATA[
<p>Well, we do at least have to eat enough food and sleep ~1/3rd of our lives. That's kinda maintenance</p>
]]></description><pubDate>Thu, 24 Sep 2026 18:25:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=49834834</link><dc:creator>dgunay</dc:creator><comments>https://news.ycombinator.com/item?id=49834834</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49834834</guid></item></channel></rss>