Hacker News: likium

New comment by likium in "“Your frustration is the product”"

likium — Thu, 19 Mar 2026 15:13:29 +0000

"Parable of the broken window", except instead of preventing the kid from throwing the rocks, they hired a someone to catch the rocks midair.

New comment by likium in "I built a demo of what AI chat will look like when it's “free” and ad-supported"

likium — Sun, 01 Mar 2026 14:14:51 +0000

We didn't see the majority switch from Google to Duckduckgo because of ads or privacy... Being the "default" brings network effects that is hard to switch away.

Show HN: Tree, but for Token Usage

likium — Sun, 01 Mar 2026 14:07:53 +0000

Treetok shows the token count for Claude and OpenAI in a directory structure. I built it because this one folder I was working in filled up the context window quick, and wanted to know why. I could have used line count instead, but I wanted more precision.

Through it, I learned that the same files in Claude cost 20-30% more tokens than OpenAI. So the same 200k context window in Claude is similar to 150k in Codex.

Comments URL: https://news.ycombinator.com/item?id=47206805

Points: 3

# Comments: 0

New comment by likium in "Nano Banana 2: Google's latest AI image generation model"

likium — Fri, 27 Feb 2026 03:47:31 +0000

Football anime doesn’t involve real people or stakes. AI can introduce a storyline, characters, etc. It won't necessarily be as popular as the real sport but I doubt the audience is zero.

New comment by likium in "Evaluating AGENTS.md: are they helpful for coding agents?"

likium — Tue, 17 Feb 2026 06:16:16 +0000

For TypeVar I’d reach for a lint warning instead.

New comment by likium in "JavaScript-heavy approaches are not compatible with long-term performance goals"

likium — Mon, 16 Feb 2026 16:51:01 +0000

As a solo dev who picked SolidJS, yes, it is a big factor. Things like tldraw, node editors, wysiwyg editors, etc. Having to reimplement them is a huge time sink.

New comment by likium in "JavaScript-heavy approaches are not compatible with long-term performance goals"

likium — Mon, 16 Feb 2026 09:15:48 +0000

There's 3x more React libraries and code out there to reference. AI agents do _a lot_ better with React than, say, SolidJS. So productivity > performance is a tradeoff that many companies seem to happily take.

New comment by likium in "Qwen-Image-2.0: Professional infographics, exquisite photorealism"

likium — Tue, 10 Feb 2026 10:06:56 +0000

At least for the real life pictures, there’s no depth of field. Everything is crystal clear like it’s composited.

New comment by likium in "Billing can be bypassed using a combo of subagents with an agent definition"

likium — Sun, 08 Feb 2026 19:17:58 +0000

For $10 flat per request up to 128k tokens they’re losing money. 100 * 100k is 10m tokens. At current api pricing that’s $50 input tokens, not even accounting for output!

New comment by likium in "Agent Skills"

likium — Tue, 03 Feb 2026 15:19:47 +0000

Just the decision of whether to allow models to invoke them has [1][2][3] different ways.

[1]: https://code.claude.com/docs/en/skills#control-who-invokes-a... [2]: https://opencode.ai/docs/skills/#disable-the-skill-tool [3]: https://developers.openai.com/codex/skills/#enable-or-disabl...

New comment by likium in "Why software stocks are getting pummelled"

likium — Mon, 02 Feb 2026 20:10:50 +0000

HN crowd did not like AI coding until it got better. How much of the AI hate is because of poor implementation?

New comment by likium in "AI’s impact on engineering jobs may be different than expected"

likium — Thu, 29 Jan 2026 20:09:06 +0000

So set up e2e tests and make sure it does things you said you wanted. Just like how you use a library or database. Trust, but verify. Only if it breaks do you have to peak under the covers.

Sadly people do not care about redundant and verbose code. If that was a concern, we wouldn't have 100+mb of apps, nor 5mb web app bundles. Multibillion b2b apps shipping a 10mb json file just for searching emojis and no one blinks an eye.

New comment by likium in "Skip is now free and open source"

likium — Thu, 22 Jan 2026 13:37:43 +0000

Equipment for any real life hobby costs money, and people are willing to pay for good equipment. Why is software so different? FOSS has made us so resistant to paying for good software. I'm not saying software has to be expensive, even $20 per major version could make a burgeoning indie industry thrive.

New comment by likium in "Predicting OpenAI's ad strategy"

likium — Sun, 18 Jan 2026 15:47:28 +0000

Supposedly Google made their own results worse to improve ad revenue. And I don't see mass migration over to Kagi or Bing.

New comment by likium in "Predicting OpenAI's ad strategy"

likium — Sun, 18 Jan 2026 15:32:52 +0000

Companies will pay OpenAI to prioritize more of their content during training. The weights for the product category will now be nudged more towards your product. Gartner Magic Quadrant for all businesses!

New comment by likium in "Predicting OpenAI's ad strategy"

likium — Sun, 18 Jan 2026 15:27:04 +0000

Go plans at $8 are getting ads too. Netflix introduced a paid plan with ads, and it is more profitable.

New comment by likium in "Ask HN: Share your personal website"

likium — Thu, 15 Jan 2026 04:33:19 +0000

https://lik.ai - Recently been adding tools like color convertors and color contrast visualizers.

New comment by likium in "AI generated music barred from Bandcamp"

likium — Wed, 14 Jan 2026 07:35:16 +0000

If someone painstakingly hand sculpted an exact replica of "David", does it make it art, or a forgery? Is hand written code to produce generative art not art?

It's difficult to pin down the line. Ultimately it's up to the individual to define them. "The relationship to art, and this kind of painting, to their work, varied with the person entirely."[1]

[1]: https://news.berkeley.edu/2025/03/31/berkeley-voices-transfo...

New comment by likium in "Google AI Studio is now sponsoring Tailwind CSS"

likium — Fri, 09 Jan 2026 04:46:36 +0000

Tailwind requires a compiler to work.

New comment by likium in "Why didn't AI “join the workforce” in 2025?"

likium — Tue, 06 Jan 2026 18:05:19 +0000

It really depends on whether coding agents is closer to "compiler" or not. Very few amongst us verify assembly code. If the program runs and does the thing, we just assume it did the right thing.