HN user
https://clementlevallois.net
Hi, I am the developer. Started the project 2 years ago. Got stuck in the fine edge cases of XML manipulation, which arise to preserve all kinds of formatting marks after translation.
Could finish with the help of GPT Sol. Added the case of translating images in slides: only when the amount of text is small enough that it will work OK.
Feedback very welcome.
Well put. Certainly my case with https://nocodefunctions.com
- traffic is slightly but noticeably decreasing for the last year: https://public.nocodefunctions.com
- it pushes me to improve the design, the overall quality, explore new feature spaces: https://next.nocodefunctions.com
Also, I noticed:
- at first LLMs apply a penalty to development: it requires to explore new toolings for AI assisted coding, then select and get used to one of them, that might well end up being a transient solution. e.g. Cursor, to be replaced soon by Claude Code?
- new uncertainty about which feature to develop: if I can develop it, then anyone else surely can reverse engineer it easily and replicate it? This is quite unnerving.
Remarkable that it echoes, from a different angle, this post from just a few days ago on HN:
https://martinalderson.com/posts/has-the-cost-of-software-ju...
This last post was largely dismissed in the comments here on HN. Simon's experiment brings new ground for the argument.
Couldn't find it on the Play store by searching for the name and the developer's name: if it is not just me then your app is very hard to discover.
So I am installing it through the link you provided, which directed me to a "install success" page saying "your purchase is successful" even if your app is free. Another obstacle to adoption :-)
Last, I was not informed on the page of the app' size. Seeing what it does and the time it takes to download I am afraid it could be huge? Third obstacle :-)
New version of nocodefunctions.com in very good shape!
-> https://next.nocodefunctions.com
A complete refactor and stack change so that the web app can be more easily extended to new functions.
Very clear thanks. I'll see if the equivalent exists in Cursor
And if I may, these advice also apply if you choose Cursor as a coding environment.
I would be interested in a book telling the history of cinema and animation that you describe
Claude Code, thank you!
I hesitate trying Claude Code, there is a bit of fatigue installing new tools :-)
By the way: ChatGPT 5.1 Codex Max pro, which was rubbish when used directly inside Cursor, is actually very good once I access it via the OpenAI Codex extension installed within Cursor!
Mysteries of toolchains...
Anyway, that proved so useful when I maxed out my Claude credits.
To nick pick, it is more about 800% gain in productivity. Cost actually increased.
I refer here to my experience as a solo developer.
With AI assistance I don't spend less hours coding, but more.
There is the thrill of shipping relevant features that were sleeping in my drawers for ages, quicker. Each hour of coding delivers just 8 x more features and bug solving.
Also, whereas I spent a few dozen dollars per month on server costs, I now also spend an equivalent amount on subscriptions and API calls to LLM services for this AI assisted coding. Worth every penny.
So while productivity increased manifold, absolute cost actually increased as well for me.
Next version of my side project, which is a site to perform text to network transformations.
Change consists in refactoring the back and front end.
Former : nocodefunctions.com:
Current: next.nocodefunctions.com
Context:
https://nocodefunctions.com/blog/jsf-primefaces-vs-htmx-alpi...
Can't connect to Claude
Not pretending to deliver definitive conclusions on the subject. Just writing down and organizing my bubbling thoughts.
Gephi is still there and maintained, actually the 2025 Gephi week takes place in August in France. True, the pace of development has slowed. What features would you like to see developed?
Refactoring the front end of my Java web app to follow basic principles of algebraic data types.
The goal is to make the code better organized, easier to read, maintain and extend.
A natural follow up: is Google's newly launched a2a better equipped to handle these security issues?
In France a local magazine for Linux enthusiasts has its cover on "Java as a language for scripting". Things are moving.
You are right IMHO. Java 24 introduces a much shorter "hello world" experience with: - no class déclaration - no void, static, public statements - no System.out
Hopefully teachers noticed...
Technology in the classroom has become an urgent issue. Laptops, smartphones, and now generative AI are increasingly depriving students of one of their most precious assets: their attention. In this blog post, I argue that these challenges demand distinct responses.
This reminds me of my time as a professor at a business school, where I worked in an open space with my screen visible to everyone. I spent a lot of time coding, so my IDE was always in plain sight.
Yet, it was only when I had the terminal open, running a few basic commands, that people would stop by and say—impressed—"Oh, I didn’t realize you could code."
Anyone competent enough here to venture a guess on the speed gain to expect under various scenarios?
Am I misreading or is Redhat "selling" its Java team to IBM? Or what? Why?
Read the story as if from the Onion and it actually fits
Yes but DeepSeek models can be accessed through the APIs of Cloudflare or GitHub, in which case no training on your data takes place.
Yes this one is a key reference:
https://www.amazon.fr/Definitive-Guide-Jakarta-Faces-Applica...
Love the concept but no clear idea of a use case.
Could you list 3 or 4 of them please?
There should be a book about Java perf / hacks derived from this challenge. I'd buy it fore sure.
I wonder how that can be leveraged for SEO
Bare metal love
And work is underway to help Gephi handle larger graphs:
https://gephi.wordpress.com/2024/06/13/gephi-week-2024-peek-...