Basit Jumani says he stopped promoting Halcyon, a photo-editing website he had built with AI assistance, after criticism made him embarrassed about it. About a month and a half later, he checked in and found that visitors were still arriving. His account is a small, personal story—not proof of independently verified growth—but it captures a useful tension: public criticism and signs of actual use are not the same thing.
Halcyon began as a project for learning by making
In a DEV Community post published October 1, 2026, Jumani describes getting interested in “vibe coding” and trying several platforms, including Replit, Bolt, Bubble, Emergent and v0, before settling on Lovable for this project. He says he used free plans to prompt and build, and began learning HTML and CSS along the way. Halcyon was AI-assisted; the point of his story is not that he built it without AI, but that making the site also became a way to learn.
As an Amazon Associate I earn from qualifying purchases.
He describes Halcyon as a photo-editing site with more than 30 presets. The current Halcyon website presents a free, no-login browser tool for color grading: upload a photo, choose a look and download the result. It says processing happens in the browser. That is the live site’s current description, which may not exactly match the version Jumani first built.
Criticism changed how he felt about the project
Jumani says some people mocked Halcyon for being AI-built and pointed to visible Lovable branding. He also recalls useful feedback and support, but says the negative reactions weighed on him. He removed references to the project, stopped promoting it and did not check it for about a month and a half.
#1 Best Overall
That response is understandable: when a project is public, comments can feel like a verdict on the work and the person who made it. But criticism is only one kind of signal. It can tell a creator how some observers feel about the tool or its presentation; it does not, by itself, establish whether the tool serves a visitor.
What he found when he returned
Jumani says Halcyon had crossed 100-plus visitors after he promoted it, then later passed 200-plus while he was inactive. He writes that people were still visiting and using it. Those figures are his account of the site’s analytics: the post does not provide an analytics export or define whether “visitors” means unique people, sessions or another measure. They should be read as self-reported counts, not audited traffic statistics.
Rank #2
He also says Google and ChatGPT began recommending Halcyon. The reviewed sources do not independently establish when or how often those recommendations appeared. The claim is part of Jumani’s account, not a verified measure of search visibility or referral traffic.
Even with those limits, his realization is clear. He had been paying close attention to the people who disliked the project and had missed the possibility that others found it useful. As he puts it, “The website was still alive.”
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What the story does—and does not—show
Jumani’s experience makes a modest point about building in public: criticism and use can coexist. A tool does not have to impress every observer to be worthwhile to someone who arrives with a specific need. He sums up his original ambition this way: “It just had to be useful enough for someone to visit, use and come back.”
- Use feedback as information, not a vote. Mockery may reveal how some people view AI-assisted work or branding, but it is not a substitute for observing whether the product helps its intended users.
- Look at the evidence you actually have. In this account, the visitor counts are self-reported and loosely defined. A creator making decisions should distinguish that kind of signal from verified analytics, repeat use, referrals or feedback from users.
- Do not confuse continued visits with automatic growth. Jumani says people kept arriving while he was inactive, but the account does not establish why, whether they returned, or whether the pattern would continue. It is not evidence that promotion is unnecessary or that a site will reliably grow on its own.
The lasting lesson is personal rather than universal: when embarrassment makes a creator look only at detractors, it can obscure the more practical question of whether anyone is finding value in the work.
Quick Recap
Best Value
Rank #4
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →




