Hacker News: devld

New comment by devld in "How Europe is killing makers and micro-entrepreneurs"

devld — Mon, 24 Aug 2026 15:19:44 +0000

Wait until Cyber Resilience Act kicks in.

New comment by devld in "2x, not 10x: coding with LLMs in 2026"

devld — Fri, 31 Jul 2026 12:16:08 +0000

This has been my experience on a recent small project for a client. I took effort to understand and prepare the spec before feeding it to Claude Opus. Yet, the result was slop full of defects, and one that I did not understand well at that. I just did not have a mental model of it. I just thought, there's no way I could ever feel confident about this code, something is missing. It did not take me long to write the important parts myself, from scratch and develop that mental model.

Then I would use Claude to make a small fix, write a unit test (write a unit test, not suggest what they unit test should be) or write some less important UI code. It just felt like old school development, with some assistance. I think we may see a shift back to a "copilot" mode and by the way, I still use GitHub Copilot. The $19 subscription includes $30 worth of credits and the autocomplete in VS code that uses some cheap model is completely free. This autocomplete is very good and I would like the market to focus more on IDE integrations. The agentic thing is either ahead of its time or it will never have time. Time will tell. I think the LLM can only be as good as the training data, so it will always excel at small chunks, but to implement entire projects of which there's such variety, I would question that. And also, how using it to implement entire projects means the developer does not hold the program model in the mind, which leads to more issues long term.

By the way, in this way of working, I see no difference between Sonnet and Opus. Sonnet is good enough to use as an aid.

New comment by devld in "Are you telling me a readonly property is wrecking my performance?"

devld — Mon, 13 Jul 2026 14:03:28 +0000

> I just assumed that readonly properties will always be pretty performant in general.

This is also the case for variables. var is faster than const, because for const (and let) the engine must do additional work (related to enforcing block-level scope, if I am not mistaken).

New comment by devld in "98% Isn't Much"

devld — Tue, 07 Jul 2026 13:57:10 +0000

I thought this would be about AI slop.

New comment by devld in "AMD Ryzen AI Halo – $4k AI Dev Kit"

devld — Tue, 07 Jul 2026 12:36:38 +0000

How well can it run GLM 5.2?

New comment by devld in "AMD Ryzen AI Halo – $4k AI Dev Kit"

devld — Mon, 06 Jul 2026 17:33:08 +0000

15 square cm box? Wow. Are there similar size, but less powered (and cheaper) workstations? I need a box that can build chromium reasonably fast and I would rather have something portable like this than a PC tower, but this is an overkill at $4k.

New comment by devld in "Claude Sonnet 5"

devld — Sun, 05 Jul 2026 15:43:36 +0000

Bedrock does not have GLM 5.2 and likely will not for quite some time. It seems like they are doing that on purpose due to pressure from Anthropic. DigitalOcean has it though.

New comment by devld in "GLM 5.2 beats Claude in our benchmarks"

devld — Sun, 05 Jul 2026 15:41:44 +0000

DigitalOcean hosts it.

New comment by devld in "AI coding is addictive. Engineers are paying the price"

devld — Fri, 03 Jul 2026 17:29:03 +0000

Or "paying the price" literally. I'm returning after a small break and into new GitHub Copilot prices. A simple question / request / analysis on Sonnet - that will be 29 cents, please. I can't imagine how much it will cost to do actual development with it.

New comment by devld in "Order a burned CD of your own public GitHub repo"

devld — Fri, 03 Jul 2026 09:14:22 +0000

Can you order chromium source if you contributed a few commits?

New comment by devld in "Anthropic requires 30 day data retention for Fable and Mythos"

devld — Fri, 12 Jun 2026 16:04:23 +0000

I think it's very likely. This is the reason why I stay on GitHub Copilot business for the time being as a solo developer. I assume that Microsoft has less incentive than Antrophic to break the business agreement and use data for training or re-sell it to Antrophic. If I was using the heavily discounted subscription plan from Antrophic, I would 100% assume everything is fed to the machine. I'd rather pay whatever the API costs, than give it an exact recipe to build my product.

New comment by devld in "I stopped tracking my time. Now I can't focus"

devld — Fri, 12 Jun 2026 11:21:38 +0000

The human brain is not made for multi-tasking. Multi-tasking will always be a productivity and focus hit. This was the point of the article.

> To me, this is similar to being honest. You don't want to depend on a system or checklist for being honest. It is something you always need, as a policy. Focus is like that. If you want to focus seriously on something, just make it a policy, and don't use all these tricks as crutches.

I found that I need a lot of guardrails and "crutches" as you said to be at peak productivity. Maybe something is wrong with me, or maybe it's the Dunning-Kruger effect.

New comment by devld in "OpenAI frontier models and Codex are now available on AWS"

devld — Fri, 05 Jun 2026 10:03:30 +0000

I think I would trust Amazon more than Antrophic, since they have no models of their own, they have no business collecting your data for training, while Antrophic most certainly does.

New comment by devld in "Brands got worse on purpose"

devld — Thu, 23 Apr 2026 12:48:10 +0000

I'm seeing this with Costa Coffee and Starbucks. They are both changing to a very cheap, plastic white, bright design. Why? So people spend as little time as possible sitting there, so there's a higher turnover.

New comment by devld in "Changes to GitHub Copilot individual plans"

devld — Wed, 22 Apr 2026 12:37:35 +0000

That was the best thing about Copilot. It was too good to last.

New comment by devld in "Vercel April 2026 security incident"

devld — Sun, 19 Apr 2026 17:24:48 +0000

Reminds me of circa 2021 Chromium bug where opening the dropdown menu on GitHub would crash the entire system on Linux. At some point, it got fixed.

New comment by devld in "Improving my focus by giving up my big monitor"

devld — Mon, 06 Apr 2026 12:11:18 +0000

Workspaces solve this problem better. Cmd + 1,2,3,4,5,6,7,8,9,0 It's like having 10 monitors in a single one. Though if I remember right, the switch is inefficient on Mac OS, but there's some workaround to that.

New comment by devld in "DigitalOcean Seeks $800M in Funding"

devld — Mon, 30 Mar 2026 19:31:07 +0000

Recently I could not get a dedicated CPU "droplet" in any of the datacenters they have.

New comment by devld in "The Impact of AI on Game Dev Jobs. Open to Work Crisis"

devld — Sun, 22 Mar 2026 15:28:20 +0000

> I've been playing with SEO for this website, and I learned that Google prefers human content because (they are not gonna say it) it needs to train, it cannot train on what it has already trained on. Google's crawler is hungry for human content

This is the reason why you can hardly trust AI companies to not train on your code. If you care about privacy, I think it's best to use Antrophic models via a third-party provider like GitHub Copilot (business) or Amazon Bedrock.

New comment by devld in "The Impact of AI on Game Dev Jobs. Open to Work Crisis"

devld — Sun, 22 Mar 2026 12:32:02 +0000

> Also, the Open to Work banner has the stink of desperation

It may as well say: "need work, bad"