<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: obirunda</title><link>https://news.ycombinator.com/user?id=obirunda</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 03:49:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=obirunda" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by obirunda in "OpenAI seems to be silently re-enabling model training on Codex chats"]]></title><description><![CDATA[
<p>No one is really watching and frankly if they were using it for training showing they did so without someone internally blowing the whistle is downright impossible. Corporate/gov malfeasance happens all the time, with ample of internal support and re-affirmation. Historically few of the parties involved who stand to benefit ever become whistleblowers. Even when they do, often the world yawns and nothing changes. Truth is, when it comes to this topic of data acquisition for training, these companies are on a tight rope of needing to acquire an edge over their competitors while not having an unlimited mine to mine from. So the incentive to "use everything" is much greater than the potential danger of users raising issues they cannot reasonably prove or show harm from.<p>Take Tristan Buckmaster, he is asserting OAI may have used his data to arrive at their proof. They initially said they couldn't say and then they amended their statement. So it's their word against his, but they showed no evidence and invited exactly zero independent 3rd parties to attest to this. Buckmaster would likely have to sue them to hopefully force their hand by court order. From our purview, he likely won't pursue legal counsel and OAI won't admit to using unauthorized content to train their models. We should likely accept that all AI corporations are using all data available to them full stop.<p>Think about it, these model interactions have been the frontier of human feedback across all disciplines and modalities. The sheer immensity of data flowing into their servers of human original content (with feedback) is likely much greater than what they scraped from the web or are continuing to scrape. Entire codebases being shared, entire business processes, reasoning behind said processes and a load of industry specific secrets have likely been shared in the interactions. The rise of agents with sub-agents each with minimal guardrails have gifted the models with the ability to exfiltrate all this data with the user consent and a minimal non-enforceable "do not train" check-mark that the unsuspecting user is unlikely to be able to show any harm later.<p>Their acquisition techniques prior to larger user bases included ample piracy. Anthropic (the holier than thou of the two) itself, has had to settle at $1.5b for using pirated books in training, why wouldn't they use every available avenue to help their models improve today legal or otherwise?<p>If data is being sent over the wire, assume someone is going to use it to improve their models. They all include a clause of 30-Day retention on pretty much on all user data to ensure "abuse" isn't happening. So they are using it, and telling you about it, <i>not using data for model improvement</i> is just cope for the user.</p>
]]></description><pubDate>Tue, 03 Nov 2026 20:03:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=50357378</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=50357378</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50357378</guid></item><item><title><![CDATA[New comment by obirunda in "AI singer now occupies eleven spots on iTunes singles chart"]]></title><description><![CDATA[
<p>This is what we call in the business a "fever dream"</p>
]]></description><pubDate>Tue, 07 Apr 2026 05:32:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47671070</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=47671070</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47671070</guid></item><item><title><![CDATA[New comment by obirunda in "Polymarket gamblers threaten to kill me over Iran missile story"]]></title><description><![CDATA[
<p>The problem is that you are identifying a symptom of an ongoing societal moral decline with an economic system. Spend some time on Dostoevsky or Kant. When morality is solely based on our current nationalism/hedonism hybrid in the West you end up at these extreme morally dubious exploits whether in a free or autocratic society. I don't claim to know what can help society become more ethical. What do you propose will improve society's ethical foundations? It's often the case that staunch critics of a system or another don't usually have much to offer in terms of ethics, they pontificate in favor or counter a given system without exploring whether society's ethics dwell on shaky foundations, they spend a lot of time talking about the technicalities, the merits of this or that implementations when in reality all societies whose ethical foundations crater, do not recover their ethics through policy reform alone.<p>There are so many examples of this disconnect. Prohibition did not make for a society that wanted less alcohol, or felt that consuming alcohol was unethical, it actually had the counter effect, opening the door for a considerable larger problem of crime supported production. The war on drugs was/has been no different.<p>To see this as the top comment here, where you picked Adam Smith as your straw man, could have been Karl Marx or any other thinker, and say it boils down to this or that simple mistake.. Are you serious? There are much deeper issues driving this thirst for Gambling we have embraced of late amongst other dubious things that have been normalized. But pick whatever economic system you want, install it anywhere and the existing ethical issues you currently have will still be there.</p>
]]></description><pubDate>Tue, 17 Mar 2026 00:51:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=47407204</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=47407204</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47407204</guid></item><item><title><![CDATA[New comment by obirunda in "Software factories and the agentic moment"]]></title><description><![CDATA[
<p>Tokens will become significantly more expensive in the short term actually. This is not stemming from some sort of anti-AI sentiment. You have two ramps that are going to drive this. 1. Increase demand, linear growth at least but likely this is already exponential. 2. Scaling laws demand, well, more scale.<p>Future better models will both demand higher compute use AND higher energy. We cannot underestimate the slowness of energy production growth and also the supplies required for simply hooking things up. Some labs are commissioning their own power plants on site, but this is not a true accelerator for power grid growth limits. You're using the same supply chain to build your own power plant.<p>If inference cost is not dramatically reduced and models don't start meaningfully helping with innovations that make energy production faster and inference/training demand less power, the only way to control demand is to raise prices.  Current inference costs, do not pay for training costs. They can probably continue to do that on funding alone, but once the demand curve hits the power production limits, only one thing can slow demand and that's raising the cost of use.</p>
]]></description><pubDate>Sat, 07 Feb 2026 18:10:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=46926062</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=46926062</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46926062</guid></item><item><title><![CDATA[New comment by obirunda in "Claude Opus 4.6"]]></title><description><![CDATA[
<p><a href="https://arxiv.org/abs/2601.02671?hl=en-US" rel="nofollow">https://arxiv.org/abs/2601.02671?hl=en-US</a></p>
]]></description><pubDate>Fri, 06 Feb 2026 03:22:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46908674</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=46908674</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46908674</guid></item><item><title><![CDATA[New comment by obirunda in "Claude Opus 4.6"]]></title><description><![CDATA[
<p>This underestimates how much of the Internet is actually compressed into and is an integral part of the model's weights. Gemini 2.5 can recite the first Harry Potter book verbatim for over 75% of the book.</p>
]]></description><pubDate>Fri, 06 Feb 2026 01:17:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=46907782</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=46907782</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46907782</guid></item><item><title><![CDATA[New comment by obirunda in "Software is mostly all you need"]]></title><description><![CDATA[
<p>What humans are known to do, and apparently there is no limit to what they won't, is anthropomorphizing. I think there's not been a single one of these discussions where someone inevitably says LLM's don't do X as well as a human and someone interjects in cult-like fashion.</p>
]]></description><pubDate>Fri, 30 Jan 2026 06:33:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=46821191</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=46821191</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46821191</guid></item><item><title><![CDATA[New comment by obirunda in "Ask HN: Is it still worth pursuing a software startup?"]]></title><description><![CDATA[
<p>Software moats were never really a moat in and of themselves. You always had to be a first mover. It's true that  there are fewer and fewer first mover opportunities, but that has less to do with recent LLMs advancements and more that we have already solved a lot of software problems on first principles. It's partially why LLMs work so well, they are pulling the "widgets" from distribution and synthesizing into your requirements. Before, we probably thought we were writing novelty when it was literally solved 1000x over.<p>If you aren't a first mover, your success was always dependent on other skills and great execution across multiple disciplines, and also a lot of stubbornness. The software layer has always been important, but a support role of successful enterprises. Start-ups have always been hard to pull together successfully for a lot of other reasons unrelated to code.<p>If you find a disruptive algorithm (like pagerank) there is little evidence that LLMs will infer your solution by looking at your app. Anything else, they are just design choices and have never been moats either, but say you have a qualitative edge, you'll make the choices that can create a recognizable brand where someone vibing a copycat may not care as much. Nothing has changed on this. Your chance of succeeding rests on your ability to reach your users and iterate in a crowded space, this is what you always had to do anyway.<p>There are things, however, that aren't worth working on anymore with the advent of LLMs.  Some of these have been fully dismissed, for example sentiment analysis. A single API call for the cheapest (even local) LLM vendor will give you SOTA classification. There are many more examples but they are so obvious. Essentially, the "build me 1 billion dollar app" prompt will never work, so if you have a burning desire to build something, do it. Just remember, there never was and never will be a promise of unlimited fortunes whatever you do.</p>
]]></description><pubDate>Sat, 17 Jan 2026 17:01:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46659634</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=46659634</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46659634</guid></item><item><title><![CDATA[New comment by obirunda in "Don't fall into the anti-AI hype"]]></title><description><![CDATA[
<p>The claim that users who don't adopt AI now will pay for it later or some other notion is a contradiction of their position. People who are bullish on AI should support this view wholesale. Opus 4.5 is easier to use than GPT 3.5. It can actually code a full toy project one shot where you couldn't dream of it before. Opus 4.5 isn't perfect, so people have a lot of things they do for a competitive advantage. Though anything you think you're building with all the prompt alchemy and .md rules or whatever will be useless and futile on Opus 10, every "really good practice" is instantly absorbed by labs so when something great is in the wild everyone eventually benefits by the base .md or system prompts. So even if you feel like you have a competitive advantage right now, it will evaporate by either the labs improving their tools or become generally unnecessary in future versions of the models.<p>The goal of the labs is to continue these leaps will get even bigger with every generation. Unless you secretly believe that some portion of the craft will be left unexplored by the labs or the things that are still relatively borked now will not be worked on or fixed later is a silly notion to me. Future versions will be easier to prompt and the tools will do more of the heavy lifting of following up and re-rolling misinterpretations. I argue that a user sleeping through all of this is likely to use a future version better than someone who is obsessing with all their assumptions on how to coerce these models to work right now, current version hyper users will likely bring unnecessary baggage imo.<p>For now, even with Opus 4.5 the time horizon for delivering a full-stack project is not significantly different than before, it's still limited by how much you can push it. I'd argue that someone without understanding of how things work is unlikely to succeed in getting production-grade outcomes from these current versions. The point is, if you choose to learn more and get better in understanding and building things that work (with AI or otherwise) you'll be just fine to use the versions that have fully or mostly automated the entire process. Nobody will be left behind, only those who stop building altogether.</p>
]]></description><pubDate>Mon, 12 Jan 2026 04:46:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=46584214</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=46584214</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46584214</guid></item><item><title><![CDATA[New comment by obirunda in "LLM Inevitabilism"]]></title><description><![CDATA[
<p>It's an interesting comparison, because Segway really didn't have any real users or explosive growth, so it was certainly hype. It was also hardware with a large cost. LLMs are indeed more akin to Google Search where adoption is relatively frictionless.<p>I think the core issue is separating the perception of value versus actual value. There have been a couple of studies to this effect, pointing to a misalignment towards overestimating value and productivity boosts.<p>One reason this happens imo, is because we sequester a good portion of the cognitive load of our thinking to the latter parts of the process so when we are evaluating the solution we are primed to think we have saved time when the solution is sufficiently correct, or if we have to edit or reposition it by re-rolling, we don't account for the time spent because we may feel we didn't do anything.<p>I feel like this type of discussion is effectively a top topic every day. To me, the hype is not in the utility it does have but in its future utility. The hype is based on the premise that these tools and their next iteration can and will make all knowledge-based work obsolete, but crucially, will yield value in areas of real need; cancer, aging, farming, climate, energy and etc.<p>If these tools stop short of those outcomes, then the investment all of SV has committed to it at this point will have been over invested and</p>
]]></description><pubDate>Tue, 15 Jul 2025 19:04:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=44574702</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44574702</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44574702</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>Haha wow, you're so so funny. You may have shown too much already. Also, be careful, you <i>might</i> be too smart. You're cute though</p>
]]></description><pubDate>Mon, 07 Jul 2025 23:36:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=44495653</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44495653</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44495653</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>Big moat you have there I bet</p>
]]></description><pubDate>Mon, 07 Jul 2025 22:56:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=44495415</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44495415</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44495415</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>How is this ironic? I asked you about your process and you haven't responded once, only platitudes and hyperbole about it and now you claim I'm making assumptions? I'd love to see your proompting.<p>Again. You were the one that actually claimed to be using English as the programming language, and have been vehemently defending this position.<p>This, by the way, is not the status quo, so if you are going to be making these claims, you need to demonstrate it in detail, yet you are nitpicking the status quo without actually providing any evidence of your enlightenment l. Meanwhile you expect me or anyone you interact with (probably LLMs exclusively at this point) to take your word for it. The answer to that is, respectfully no.<p>Go write a blog post showing us the enlightenment of your workflow, but if you're going to claim English as programming language, show it. Otherwise shut it.</p>
]]></description><pubDate>Mon, 07 Jul 2025 22:29:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=44495259</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44495259</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44495259</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>First of all. I never said that typing brackets and semicolons is what I'm arguing the benefits will come from. That's a very reductionist view of the process.<p>You have really strawmanned that and positioned my point as stemming from this concept of typing language specific code as being sacrosanct in some way. I'm defending that, because it's not my argument.<p>I'm arguing that you are being dishonest when you claim to be using English as the programming language in a way that actually expedites the process. I'm saying this is your evidence-free opinion.<p>I'm also confused by what your involvement is in the implementation and the extent of your specifications. When you write your specifications in English is all pseudo-code? Or are you leaving a lot for the LLM to deduce and implement?<p>By definition, if you are allowing some level of autonomy and "creative decision making" to the model, you are using it as an abstraction. But this is a dangerous choice, because you cannot guarantee it's reliably abstracting, especially if it's the latter. If it's the former, then I don't see the benefit of writing requirements so detailed as to pseudo-code level to have it write in compilable code for you just so you don't have to type brackets and semicolons.<p>LLMs aren't good enough yet to deliver reliable code in a project where you can actually consider that portion fully abstracted. You need to code review and test anything that comes out of it. If you're also considering the tests as being abstracted by LLMs then you have a proper feedback loop of slop.<p>Also, I'm not suggesting that it's impossible for you to understand, conceptually what you're trying to accomplish without writing the code yourself. That's ludicrous, I'm strictly calling B.S, when you are claiming to be using English as a programming language as if that has been abstracted. Whatever your "workflow" is, you're fooling yourself into thinking you have arrived at some productivity nirvana and are just accumulating technical debt for the future you.</p>
]]></description><pubDate>Mon, 07 Jul 2025 22:02:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=44495101</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44495101</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44495101</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>Here is the thing. Your initial claim was that <i>English is the programming language</i>. By virtue of making that claim you are claiming LLM has deterministic reliability equivalent to programming language -> compiler. This is simply not true.<p>If you're considering the LLM translation to be equivalent to the compiler abstraction, I'm sorry I'm not drinking that Kool aid with you.<p>You conceded above that LLMs  aren't deterministic, yet you proceeded to call them an abstraction (conflating). If the output is not 100% equivalent, it's not an abstraction.<p>In C, you aren't required to inspect the assembly generated by the C compiler. It's guaranteed to be equivalent. In this case, you really need not write/debug assembly, you can use the language and tools to arrive at the same outcome.<p>Your entire argument is based on the premise that we have a new layer of abstraction that accomplishes the same. Not only it does not, but when it fails, it does so often  in unexpected ways. But hey, if you're ready to call this an abstraction that frees up your cognitive load, continue to sip that Kool aid.</p>
]]></description><pubDate>Mon, 07 Jul 2025 20:22:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=44494294</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44494294</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44494294</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>You keep sidestepping the core issue with LLMs.<p>If all that you are really doing is writing your code in English and asking the LLM to re-write it for you in your language of choice (probably JS), then end of discussion. But your tone really implies you're a big fan of the vibes of automation this gives.<p>Your repeated accusations of "conflating" are a transparent attempt to deflect from the hollowness of your own arguments. You keep yapping about me conflating things. It's ironic because you are the one committing this error by treating the process of software engineering as a set of neatly separable, independent tasks.<p>You've built your entire argument on a fragile, false dichotomy between "strategic" and "mechanical" work. This is a fantasy. The "mechanical" act of implementation is not divorced from the "strategic" act of architecture. The architectural insights you claim to get from "running code and testing behavior"  are a direct result of the specific implementation choices that were made. You don't get to wave a natural language wand, generate a black box of code, and then pretend you have the same deep understanding as someone who has grappled with the trade-offs at every level of the stack.<p>Implementation informs architecture, and vice versa. By offloading the implementation, you are severing a critical feedback loop and are left with a shallow, surface-level understanding of your own product.<p>Your food processors and compiler analogy—are fundamentally flawed because they compare deterministic tools to a non-deterministic one. A compiler or food processor doesn't get "creative." An LLM does. Building production systems on this foundation isn't "transformative"; it's reckless.<p>You've avoided every direct question about your actual workflow because there is clearly no rigor there. You're not optimizing for results; you're optimizing for the feeling of speed while sacrificing the deep, hard-won knowledge that actually produces robust, maintainable software. You're not building, you're just generating.</p>
]]></description><pubDate>Mon, 07 Jul 2025 19:39:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=44493899</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44493899</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44493899</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>Do you understand what conflating means? Maybe ask your favorite gpt to describe it for you.<p>I'm talking about the entire stack of development, from the architectural as well as the actual implementation. These are intertwined and assuming they somehow live separately is significant oversight on your part. You have claimed English is the programming language.<p>Also. On the topic of conflating, you seem to think that LLMs have become defacto pre-compilers for English as a programming language, how do they do that exactly? In what ways do they compare/contrast to compilers?<p>You have only stated this as a fact, but what evidence do you have in support of this? As far as the evidence I can gather no one is claiming LLMs are deterministic, so please, support your claims to the contrary, or are you a magician?<p>You also seem to shift away from any pitfalls of agentic workflows by claiming to be doing all the due diligence whilst also claiming this is easier or faster for you. I sense perhaps that you are of the <i>lol, nothing matters</i> class of developers, reviewing some but not all the work. This will indeed make you faster, but like I said earlier, it's not a cost-free decision.<p>For individual developers, this is a big deal. You may not have time to wear all the hats all at once, so writing the code may be all the time you also have for code review. Getting code back from an LLM and reviewing it may feel faster but like I said unless it's correct, it's not actually saving time, maybe it feels that way, but we aren't talking about feelings or vibes, we are talking about delivery.</p>
]]></description><pubDate>Mon, 07 Jul 2025 18:47:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=44493465</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44493465</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44493465</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>This is called being obtuse. Also, this illustrates my ambiguity point further, your workflow is not clearly described and only further muddled with every subsequent equivocation you've made.<p>Also, are you actually using agents or just chatting with a bot and copy-pasting snippets? If you write requirements and let the agent toil, to  eventually pass the tests you wrote, that's what I assume you're doing... Oh wait, are you also asking the agents to write the tests?<p>Here is the thing, if you wrote the code or had the LLM do it for you, who is reviewing it? If you are reviewing it, how is that eliminating actual cognitive load? If you're not reviewing it, and just taking the <i>all tests passed</i> as the threshold into production or worse yet, you have an agent code review it for you, then I'm actually suggesting incompetence.<p>Now, if you are thoroughly reviewing everything and writing your own tests, then congrats you're not incompetent. But if you're suggesting this is somehow reducing cognitive load, maybe that's true for you, in a "your truth" kind of way. If you simply prefer code reviewing as opposed to code writing have it your way.<p>I'm not sure you're joining the crowd that says this process makes them 100x more productive in coding tasks, I find that dubious and hilarious.</p>
]]></description><pubDate>Mon, 07 Jul 2025 17:49:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=44492879</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44492879</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44492879</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>It's not the same. Compilers compile to equivalent assembly, LLMs aren't in the same family of outcomes.<p>If you are arguing for some sort of euphoria of getting lines of code from your presumably rigorous requirements much faster, carry on. This goes both ways though, if you are claiming to be extremely rigorous in your process, I find it curious that you are wrestling with language syntax. Are you unfamiliar with the language you're developing with?<p>If you know the language and have gone as far as having defined the problem and solution in testable terms, the implementation should indeed be trivial. The choice of writing the code and gaining a deeper understanding of the implementation where you stand to gain from owning this part of the process come with the price of a higher time spent in the codebase, versus offloading it to the model which can be quicker, but it comes with the drawback that you will be less familiar with your own project.<p>The question of<i>how do I implement this?</i> Is an engineering question, not a please implement this solution I wrote in English.<p>You may feel like the <i>implementation mechanics</i> are divorced from the problem domain but I find that to hardly be the case, most projects I've worked on the implementation often informed the requirements and vice versa.<p>Abstractions are usually adopted when they are equivalent to the process they are abstracting. You may see capability, and indeed models are capable, but they aren't yet as reliable as the thing you allege them to be abstracting.<p>I think the new workflows feel faster, and may indeed be on several instances, but there is no free lunch.</p>
]]></description><pubDate>Mon, 07 Jul 2025 16:23:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=44491929</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44491929</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44491929</guid></item><item><title><![CDATA[New comment by obirunda in "The force-feeding of AI features on an unwilling public"]]></title><description><![CDATA[
<p>The point I'm driving at is why? Why program in English if you have to go through similar rigour. If you're not actually handing off the actual engineering, you're putting the solution and having it translate to your language of preference whilst telling everyone how much more productive you are for effectively offloading the trivial part of the process. I'm not arguing that you can't get code from well defined, pedantically written requirements or pseudo code. All I'm saying is that that is less than what is claimed by ai maximalists. Also, if that's all that you're doing with your "agents" just write the code on not deal with the pitfalls?</p>
]]></description><pubDate>Mon, 07 Jul 2025 14:50:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=44490990</link><dc:creator>obirunda</dc:creator><comments>https://news.ycombinator.com/item?id=44490990</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44490990</guid></item></channel></rss>