--- title: Is it all just vapourware? — Kira Howe | daily.dev description: A software engineer shares frustration with the current state of AI agent tooling, arguing that most of it is vapourware. Using ONA as a case study, she... canonical: https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Is it all just vapourware? — Kira Howe | daily.dev og:description: A software engineer shares frustration with the current state of AI agent tooling, arguing that most of it is vapourware. Using ONA as a case study, she... og:url: https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl og:image: https://api.daily.dev/og/posts/xJTfL01gL.png og:image:alt: Is it all just vapourware? — Kira Howe og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Is it all just vapourware? — Kira Howe **[Hacker News](https://daily.dev/sources/hn)** · 4 min read · 0 upvotes · 0 comments ## Summary A software engineer shares frustration with the current state of AI agent tooling, arguing that most of it is vapourware. Using ONA as a case study, she describes spending nearly $20 in compute credits just to watch the agent fail to retrieve todos from Linear — never getting to actual development work. The core critique: these tools add friction rather than removing it, their marketing wildly overpromises, and the companies building them are themselves the best proof that agentic development doesn't work as advertised. The author still believes in the concept but wants a version that actually delivers. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What happened when I tried ONA for agentic development on a real project? ONA failed to deliver on its promise of end-to-end automated development. After struggling past a broken desktop login, the platform consumed nearly an entire $20 allotment of 'ona compute units' just attempting to retrieve todos from Linear — never reaching actual implementation work. The experience added friction rather than removing it, with more integrations to debug, auth tokens to manage, and bills to track. _Developers evaluating AI agent platforms before spending money track real-world experiences like this on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 148 comments across hackernews (as of 2026-08-10). **TL;DR:** The community is sharply divided: a vocal contingent agrees that agentic AI tooling overpromises and underdelivers, while others insist the tools genuinely work if used correctly — but neither side can fully convince the other, and the debate quickly broadens into whether claimed productivity gains are real at all. **Sentiment:** 25% positive · 35% mixed · 40% skeptical **The case for** - LLMs can deliver meaningful time compression on well-scoped, specific tasks like SIMD optimization or boilerplate generation. - Used in tight, guided loops with human oversight, AI assistance can accelerate certain classes of work (cross-codebase refactors, test writing). - Some commenters report real greenfield project speedups, and there is documented evidence of AI-assisted commits landing in major codebases like the Linux kernel. **The pushback** - Large AI-generated PRs often contain subtly wrong abstractions and incorrect assumptions, making review more burdensome than writing the code manually. - Claimed 10x productivity gains are not visible in open-source project velocity, feature output, or maintainer experience — raising doubts about whether the gains are real or just performative. - AI agents add friction (auth tokens, integrations, debugging loops) rather than removing it, and the models forget lessons between sessions. - Codebases built heavily with AI assistance tend to rot quickly as architectural debt accumulates faster than it can be managed. - Open-source projects that initially welcomed AI contributions largely reversed course after finding the quality universally poor. **By community** - hackernews (mixed): Deeply split between developers who find genuine but narrow utility in LLMs and those who see the productivity claims as unsupported by any observable evidence in the wild. **Hottest debate:** Whether claimed 10x productivity gains from LLMs are real, given the near-total absence of visible evidence in open-source project velocity or contribution quality. **Open questions** - If senior engineers are quietly using AI to produce high-quality code, why is there no measurable acceleration in open-source feature development or new project creation? - At what point does the overhead of reviewing, correcting, and maintaining AI-generated code outweigh the speed benefit of generating it? - Are the productivity gains from AI coding tools only materializing in proprietary, low-accountability environments where code quality was never the real measure of success? **Highlights** > >If agentic development actually worked the way any of them say it does I think its fascinating just how much of a gap there is between what's being claimed, and the verifiable observable data of the open source world. Major open source projects are by and large starting to ban LLMs now, because the contributions made by LLM users have been universally terrible and unhelpful. There doesn't appear to be a single major project that's found generating code to lead to major productivity speedups, and the consensus appears to be that its just lead to a lot of crappy contributions that are harder to spot immediately as being obvious crap I regularly see people claim that they are now 10x more productive with LLM code generation, and I just wonder where all the code is. Is it somehow true that these gains are only being realised in proprietary projects, and not a single one of them has put even a small fraction of their new found engineering powers into eg Godot? Why do only the poor quality LLM code generation users make PRs to open source projects, and never the engineers that know how to really use it correctly? If you look in the open source major project space, you can find almost no evidence that AI code generation exists at all. Go browse your favourite critical tool and look for AI generated PRs that have landed in the codebase, its probably a tiny handful of them in comparison to the human written PRs prior to an LLM ban. It turns out that once you have a verifiable, open quality review bar, for some reason almost no LLM commits really meet the level of quality necessary I strongly suspect that what we're seeing is that much of the tech code-writing economy had already become completely performative prior to AI turning up. It no longer matters in the current age if your code is good, or works, because your job is to give the illusion of product development while the stock market price gets pumped, until you all cash out your share value, get bought, or hop jobs in 2 years. For many companies it literally does not matter if you produce anything that generates value (or works), because the illusion of progress is all that matters. AI is absolutely incredible at creating the illusion of progress, because it looks a whole lot like real code, it just appears to have failed the bar of making actual projects that work. If that was never the goal in the first place, it probably really is a 10x productivity boost > — [20k on hackernews · 10 comments](https://news.ycombinator.com/item?id=49236335) > I did but it was followed by "holy shit now I gotta review this +3000 -500 LOC PR full of subtly wrong abstractions, needless diversions and incorrect assumptions". People keep repeating your sentiment here but I simply can't follow, are we even on the same planet? Or did everyone switch to just not caring about maintainability and code quality anymore? Or are your work tasks simply so mindnumbingly, stupidly simple that even an AI can oneshot them properly? I mean this honestly btw, not dismissively like some sister comments. The gap between the productivity increases people report on HN and what I experience myself is insane. In fact, if I factor in the procrastination I find myself doing on dotting the i's on a supposedly "one-shotted" AI implementation of a nontrivial feature, I think the AI actively slows me down. The only way I've found that I can actually use AI productively and sustainably is in very small tight loops and, well, at that point it's not that much faster than just typing in the code (with the occasional "Cursor Tab" complete). Am I doing something wrong? > — [skrebbel on hackernews · 6 comments](https://news.ycombinator.com/item?id=49236311) > Wait, only six weeks ago? That's not long enough to be reporting success, genuinely. Come back in a few months, bare minimum. I'm far from a skeptic, but I've also personally had a number of moments over the past 12 months where I've declared "this is the future!" about some new app I vibe-coded, or some new workflow I started following, only to abandon it a few weeks later. And it's not just me. Check back in on many of the vibe-coded projects or AI tools you see shared and you'll see the same. It's happened at my work too — people taking over entire meetings to discuss their new revolutionary AI workflow and then, a week later, nothing... A big problem is that these codebases rot. Agents move incredibly fast at first, but then as you pay less attention (or perhaps no attention at all) to the architecture, they slowly fall to bits. So then you decide, I'll use AI to rewrite it! And it gets better for a while until, well, you get it. That's not to say there isn't value here, there absolutely is, just — chill. A little. > — [sandcat\_ on hackernews](https://news.ycombinator.com/item?id=49236515) > If you want to see contributions to Linus that used AI you can search for commits with tags that look like this in their commit message: Assisted-by: Codex:gpt-5.5 Assisted-by: Claude:claude-opus-4.8 This search on GitHub seems to find about 2,000 of those: repo:torvalds/linux assisted-by (claude OR codex) https://github.com/search?q=repo%3Atorvalds%2Flinux+assisted... ... but if you clone the git repo you can get an exact count of 824 commits (not sure why the search over-counted). Here's a good candidate for a material performance improvement: https://github.com/torvalds/linux/commit/e1bf79628453e6afac8... Single-stream throughput (MB/s): Before After Change seq-write/dontcache 298 897 +201% rand-write/dontcache 131 236 +80% > — [simonw on hackernews](https://news.ycombinator.com/item?id=49237585) > > But so far most of what they do is make more annoying work for me. More integrations to debug, more auth tokens to refresh, more bills to keep track of, more meandering and drawn out descriptions of non-bugs with bogus fix suggestions and misinformed “root cause” analyses. It’s tiresome. God this times 1000. I'm so sick of having AI chase a bug and having to lead it by the hand like a toddler to try and help me solve bugs. The difference is, a toddler learns when you explain. An LLM holds your responses in context and uses them to generate more authentic sounding garbage, but next session, foomf, the lesson is unlearned again. I had a tiny problem with prerendering not working on a react site last night, I must have spent close to an hour running commands it asked me to run like a moron, verifying dumb things I had already checked like "did the file actually upload to ftp" or had I restarted Apache or was there some magic htaccess file somewhere. Eventually I just gave up on Claude and tried some different paths in Apache virtual host settings and it worked. Of course if I went back to Claude and reported that, as would be my instinct with a human, it would confidently explain why that was the bug, why it couldn't spot the issue, and how smart I am for finding it. And then it would forget everything tomorrow > — [trencedamp on hackernews · 2 comments](https://news.ycombinator.com/item?id=49236182) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=49235859) · 67 points · 148 comments ## Similar posts on daily.dev - [AWS says almost 90% of Amazon’s early AI agent prototypes never shipped](https://daily.dev/posts/aws-says-almost-90-of-amazon-s-early-ai-agent-prototypes-never-shipped-nz5oy4r9c) · The Next Web · 1 upvotes · 0 comments - [Software Will Never Die](https://daily.dev/posts/software-will-never-die-mdkre4lkp) · marmelab · 3 upvotes · 1 comments - [AI Is Really Weird](https://daily.dev/posts/ai-is-really-weird-lmlltzrmc) · Where's Your Ed At · 66 upvotes · 3 comments - [Your coding agent got the onboarding your developers never did](https://daily.dev/posts/your-coding-agent-got-the-onboarding-your-developers-never-did-z8h70sipe) · The New Stack · 3 upvotes · 2 comments - [Leveraging AI as a Developer: Creating Developer Tools](https://daily.dev/posts/leveraging-ai-as-a-developer-creating-developer-tools-mgadsenbd) · Atomic Spin · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#vibe-coding](https://daily.dev/tags/vibe-coding) [View this post on daily.dev](https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Is it all just vapourware? — Kira Howe","url":"https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl"},"datePublished":"2026-08-09T21:33:32.500Z","dateModified":"2026-08-10T00:27:48.454Z","description":"A software engineer shares frustration with the current state of AI agent tooling, arguing that most of it is vapourware. Using ONA as a case study, she...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4c1cc3f932bd8f8a079a06847d6a7f83?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4c1cc3f932bd8f8a079a06847d6a7f83?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,vibe-coding","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Is it all just vapourware? — Kira Howe"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/is-it-all-just-vapourware-kira-howe-xjtfl01gl#faq","mainEntity":[{"@type":"Question","name":"What happened when I tried ONA for agentic development on a real project?","acceptedAnswer":{"@type":"Answer","text":"ONA failed to deliver on its promise of end-to-end automated development. After struggling past a broken desktop login, the platform consumed nearly an entire $20 allotment of 'ona compute units' just attempting to retrieve todos from Linear — never reaching actual implementation work. The experience added friction rather than removing it, with more integrations to debug, auth tokens to manage, and bills to track. Developers evaluating AI agent platforms before spending money track real-world experiences like this on daily.dev."}}]} ```