Hacker News: alentred

New comment by alentred in "Every GPU That Mattered"

alentred — Tue, 07 Apr 2026 19:20:54 +0000

Awwww..., this brings so many memories. I had almost all of the early ones: Voodoo 2, Riva TNT2, then GeForce 3 (I think...). Then I switched to laptops and didn't have a discrete graphics till last year when I started playing with LLMs locally. So basically I jumped from GeForce 3 to RTX 3090 :) Thank you for bringing those memories back!

Which Programming Language Is Best for Claude Code?

alentred — Tue, 24 Mar 2026 23:56:00 +0000

Article URL: https://dev.to/mame/which-programming-language-is-best-for-claude-code-508a

Comments URL: https://news.ycombinator.com/item?id=47511304

Points: 4

# Comments: 0

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

alentred — Thu, 19 Mar 2026 14:49:30 +0000

> the equivalent of a broadcast TV channel that only showed 7 minutes of actual TV content per hour, devoting the other 53 minutes to paid commercials

Yes, I tried YouTube iOS app recently, without an ad blocker. It pretty much describes the experience.

New comment by alentred in "No leap second will be introduced at the end of June 2026"

alentred — Mon, 09 Mar 2026 21:39:05 +0000

I would rather suggest a contrary: do smaller increments more frequently. This way it is easier to test and if something goes wrong you know it quicker. Kind of like running your CI pipeline on every commit vs nightly. Going to millisecond adjustments seems, however, very impractical.

New comment by alentred in "[dead]"

alentred — Sat, 07 Mar 2026 19:30:36 +0000

Nah, T-800 is the best. T-1000 was supposed to replace it, but T-800 won.

New comment by alentred in "Elevator Saga: The elevator programming game (2015)"

alentred — Wed, 04 Mar 2026 14:08:35 +0000

Solving it with Claude is a totally different kind of fun of course. But anyway, Claude browser extension is very good at it. I sent it the initial prompt, and then asked it to continue on each next challenge. It passed first 5 challenges on the fly, and started to struggle on challenge 6, which it solved after 4 attempts. I stopped at that point because the fun was depleted.

It's like role-playing a story of software developer in the era AI, but accelerated. The results are truly good and fast. Coding fun zero. The new fun is prompt/context engineering.

You are a JavaScript developer. On this page you are presented with a coding challenge to solve: an elevator to program in JavaScript. Analyze the page, take a screenshot to understand the floor and elevator layout (how many floors, how many elevators), see the sample code in the solution text box and replace it with your solution for the challenge. Keep the solution simple, just sophisticated enough to solve the task at hand, do not over-engineer or optimize, not unless your initial solution fails. After you insert the solution into the text box, click the "Start" button to test it. After a time limit set for a solution (it is indicated on a page), verify if the solution worked: read page or take screenshot. If it didn't work, try a new better solution. If it worked, you task is complete. See the API documentation here: https://play.elevatorsaga.com/documentation.html#docs .

New comment by alentred in "Claude is an Electron App because we've lost native"

alentred — Tue, 03 Mar 2026 22:21:06 +0000

Having said (read) that, I am surprised there is still no official Claude Desktop app for Linux. :'(

New comment by alentred in "Cardiorespiratory fitness is associated with lower anger and anxiety"

alentred — Tue, 24 Feb 2026 19:16:37 +0000

We lack basic education in fitness, really, we do! They don't teach it in schools, but really just walking your 8-10k steps a day + simple own-weight exercises at home do wonders! Gym is fine for those who like it and can afford it (time, money), but by far not the only solution. We need to educate ourselves better. Plus, better cities, I am with you on that one.

New comment by alentred in "Anthropic tries to hide Claude's AI actions. Devs hate it"

alentred — Mon, 16 Feb 2026 12:50:21 +0000

Well, there is OpenCode [1] as an alternative, among many others. I have found OpenCode being the closest to Claude Code experience, and I find it quite good. Having said that I still prefer Claude Code for the moment.

[1] https://opencode.ai/

New comment by alentred in "No Coding Before 10am"

alentred — Sun, 15 Feb 2026 10:14:19 +0000

> Code is context, not a library. Data is the real interface.

I don't *yet* subscribe to the idea of "code is context for AI, not an interface for a human", but I have to admit that the idea sounds feasible. I have many examples of small-to-mid size apps (local use only) where I pretty much didn't even look at the code beyond checking that it doesn't do anything finicky. There, the code doesn't mater because I know that I can always regenerate it from my specs, POC-s, etc. I agree that the paradigm changes completely if you look at code as something temporary that can be thrown away and re-created when the specification changes. I don't know where this leads to and if this is good or not for our industry, but the fact is - it is feasible.

I would never use this paradigm for anything related to production, though. Nope. Never. Not in the foreseeable future anyway.

> Everyone uses their own IDE, prompting style, and workflow.

In my experience with recent models this is still not a good idea: it quickly leads to messy code where neither AI nor human can do anything anymore. Consistency is key. (And abstractions/layers/isolation everywhere, as usual).

IDE - of course. But, at the very least, I would suggest using the same foundation model across the code base, .agent/ dirs with plenty of project documents, reusable prompts, etc.

P.S. Still not sure what does the 10AM rule bring, though...

New comment by alentred in "Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs"

alentred — Tue, 10 Feb 2026 09:25:53 +0000

Oh, sorry for misunderstanding - I am not criticizing or accusing of anything at all!, but suggesting ideas for further research. The practical applications, as I mentioned above, are all there, and for what its worth I liked the paper a lot. My point is: I wonder if this can be followed up by a more so-to-say abstract research to drill into the technicalities of how well the models follow the conflicting prompts in general.

New comment by alentred in "Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs"

alentred — Tue, 10 Feb 2026 08:11:17 +0000

If we abstract out the notion of "ethical constraints" and "KPIs" and look at the issue from a low-level LLM point of view, I think it is very likely that what these tests verified is a combination of: 1) the ability of the models to follow the prompt with conflicting constraints, and 2) their built-in weights in case of the SAMR metric as defined in the paper.

Essentially the models are given a set of conflicting constraints with some relative importance (ethics>KPIs), a pressure to follow the latter and not the former, and then models are observed at how good they follow the instructions to prioritize based on importance. I wonder if the results would be comparable if we replace ehtics+KPIs by any comparable pair and create a pressure on the model.

In practical real-life scenarios this study is very interesting and applicable! At the same time it is important to keep in mind that it anthropomorphizes the models that technically don't interpret the ethical constraints the same was as this is assumed by most readers.

Ask HN: Will GPU and RAM prices ever go down?

alentred — Sat, 07 Feb 2026 17:16:23 +0000

A good graphics card costs a lot ever since the cryptomining fever, and RAM is a more recent case. Assembling a gaming or a "local AI" PC is practically out of question today given the budget needed - prices just don't sound reasonable, regardless of whether affordable or not. What's your take - are living in this world from now on, or will it revert, and why?

Comments URL: https://news.ycombinator.com/item?id=46925529

Points: 2

# Comments: 5

The Year Ahead 2026: Optimism with Footnotes (By Bill Gates)

alentred — Tue, 27 Jan 2026 16:25:48 +0000

Article URL: https://www.gatesnotes.com/work/save-lives/reader/three-tough-truths-about-climate

Comments URL: https://news.ycombinator.com/item?id=46782124

Points: 4

# Comments: 0

New comment by alentred in "Vibe coding kills open source"

alentred — Mon, 26 Jan 2026 14:36:33 +0000

Not an answer to all of our problems, but I wonder if we will see a wider adoption of more complex contribution models. Like "Lieutenants Workflow" Linux was known for, for example. Many possible workflows are explored in the Git Book [1].

[1] https://git-scm.com/book/en/v2/Distributed-Git-Distributed-W...

Tell HN: Thoughtfully https://claude.md redirects to Claude Code docs

alentred — Mon, 26 Jan 2026 11:59:19 +0000

I accidentally clicked on a accidentally created link in Notion (typed in "CLAUDE.md", Notion converted it to a link) and noticed this.

I am just very fond of and sympathetic to this level of care and the attention in software, and wanted to say: hats off to Anthropic Team.

Comments URL: https://news.ycombinator.com/item?id=46764595

Points: 1

# Comments: 0

New comment by alentred in "Software engineers can no longer neglect their soft skills"

alentred — Sun, 18 Jan 2026 14:51:49 +0000

Not the original author, but I would guess that understanding the domain problem and interpreting it correctly in a software solution (not code, but a product with workflows, UX, etc.), which in turn requires ability to listen and understand and ask right questions on one hand (what a user wants to achieve), and a good understanding of the technical limitations as well as human habits on the other hand (what is possible and makes sense). One can argue that AI lacks what we'd call intuition and interpersonal qualities which are still necessary, as before AI.

New comment by alentred in "The longest Greek word"

alentred — Sun, 18 Jan 2026 08:40:36 +0000

The two words that struck me are this chemical compound [1] (quite artificial as a name if you ask me, but apparently considered as a word), and this perfectly real hill name [2]

[1] https://en.wiktionary.org/wiki/Appendix:Protologisms/Long_wo...

[2] https://en.wikipedia.org/wiki/Taumatawhakatangi%C2%ADhangako...

New comment by alentred in "The struggle of resizing windows on macOS Tahoe"

alentred — Mon, 12 Jan 2026 11:06:50 +0000

Modern interfaces are digging a bigger and bigger gap between UI and UX, while UI-UX is actually a balancing act.

Let's face it, new glass UI is stunning - not for everyone's taste, like everything in art - but it has the Wow effect. Fresh look, transparency, new colors, wow! Same goes to many, not all, web sites, apps, etc.

On the UX side, with some exceptions, it is a disaster, though. Why on Earth would I want an ill-readable text behind a semi-transparent panel? Windows that only use 90% of my OLED screen I paid for? Do I want every web app invent its own navigation? Not in my worst dreams.

I like the new UIs, designers do an excellent job. Now, we must also bring back the UX people! Real user-oriented UX, not dark patterns UX that trick users to sign up for services they don't need. Its a pity, the latter actually killed the UX domain I think.

New comment by alentred in "People who come off slimming jabs regain weight four times faster than dieters"

alentred — Fri, 09 Jan 2026 14:20:58 +0000

Similarly, people get their weight back after liposuction, or after stopping the diet, as the article posits.

This boils down to the fact that the weight, and its quality (fat vs muscle) is a function of habits.

Given the number of studies that show the complexity of factors that influence the weight, from neuroscience and psychology to studies of metabolism, it is a wishful thinking to have an injection or a pill alone as a long-lasting solution.