allan_s

Is it better than letting claude code use python directly ? Especially on those 3 metrics: 1. better prompt adherence 2. visually more pleasing 3. token consumption

Especially as I think claude code got some reinforcement learning on these use cases ?

I think the source of your issue is in your statement itself, why do you want a task that evaluate things as broad to be only a coding task ? Shouldn't it be a planning task, documentation task, knowledge retrieval task etc. And very certainly not with just an initial prompt but an existing codebase + existing doc + tickets ?

Is "the layout scream AI generated" the new Bootstrap ? I.e what people use to quickly convey their ideas (bad or good)

Ironically, for myself at least, the least it looks AI, the more I've spent time prompting for it to not look AI.

Fortunately hr system in most companies are from software vendors that are 2 gen behind so a mcp with a "fire $EMPLOYEE " tool will not come up

Would also be funny if it fires the one who done the request.

Why ? The comment I was replying to was not about the kids ?

At the same time I opened netflix and it started cycling around and I got a very gory scene from the walking dead and my intent "show me something to watch" was even more ambigous and implicit.

Long before AI I remember asking people in code review to add comments specifically to make the code grep-able. Same for for privileging key value mapping to dynamic string concatenation.

I dont have twitter so my thought reading the post

1. Wow i want to do that too !

2. Wait is there a follow up on how to reproduce this at home

3. Does it mean i will have my "full" dna sequence ?

4. If not, what would be missing (my understanding is that dna while dns is static, genes get activated /deactivacted depending on a lot of factors ? And how to get these missing parts?

5. What are the pratical current and future use of it ? Can i see my family doctor with it ?

I think what the author meant is that it does help not more than the same knowledge provided the old way.

Sorry, I have lived and worked there 6 years in different cities and I do speak a fluent (though with a very heavy French accent) mandarin. It's totally not my projection but my experience first hand.

During the "diaoyu island" incident in the 2010s the sushi shop 200m near my appartment got sacked, and all japanese-brand car get smashed.

My black (and indian) friends all complained how hard they were treated. And when talking with my Chinese friends they all had very .... interesting... point of view.

Edit: also, I'm not from the US

Ask a gay, a black or a Japanese how it feels living in China.

I also wonder how practical it was to climb there, I went to the eiffel tower several times and climbing stairs is an exercice by itself ,especially spiral ones

As a ESL, what is unnatural in the language used ?

As someone who spent quite some times these days to reverse the figma protocol[0] I can't agree more with

Figma accidentally excluded themselves from the training data that would have made them relevant in the agentic era.

Their binary format is so much of a "let's reinvent everything" which I think come from the fact it's a tool you can use for web design, android app design, ios design and anything-you-want design that it became a jack of all trade and so mapping it to web is not a perfect 1:1 translation.

And for being useful to agent, any people who got to implement the figma from a UX guy know that even human can't know truly the intent of most figma design, so how a LLM could ? Common source of question that even the UX guy has no answer for:

  1. Ok this button looks great, but in German how will it look ? 
  2. Oh and actually this button does not look great when i put in CSS, it wraps on two line, you cheated again with the letter spacing, did you ?
  3. How does it look on a phone that is not an iphone ? 
  4. You know that doing a border with a gradien is not possible in CSS, so what should i put ?
  5. How does it look on a 4k screen ?
  6. etc.

So I can't wait for these tools that are html behind to catch up, even more if we can have the prompt with it. (As a developer I never got to see the prompt the product manager made to the UX guy)

[0]https://github.com/allan-simon/figma-kiwi-protocol

that's what I'm telling my non-tech friends when they say "Looking to how fast AI progress and robotics, me as an electrician, will a robot soon take my job?" I reply to them "My job as a software engineer will be replaced sooner than yours, because for your job, the robot will be much more expensive than the minimal wave, and you don't need to buy a human"

Are these ugly and hard to use website made by people who did want to be unique ?

Its the same for a lot of bundled things, mac hardware + os or windows pre-installed, chrome being pushed by google.com etc.

I did that with my kids and it was pretty cool !

I've also been using the LLM in Posthog and it has been impressive. I need to check if I can also plug a MCP/Skill to my actual claude code so that I can cross reference the data from my other data source (stripe, local database, access logs etc.) for in depth analysis

But then we also can't request 50% of CEOs being women or any job with that arguments ? Wouldn't it be more fair to be excused if you actually can prove that you're taking care of familly members regardless of man/woman ? Why would a perfectly able 20 year old woman be excuzed by default based on her sex ?

thanks!

I find it ironic to have it named "catalan(g)" on a post about spanish law.

homelessness is not just a house problem. https://pmc.ncbi.nlm.nih.gov/articles/PMC2605901/

most people don't become homeless because they don't have a house, but because they lost/lack the way to keep one. And not only on the financial plane.

the same as your browser trust some https domain. A list of "high trust" org that you can bootstrap during startup with a wizard (so that people who don't trust Mozilla can remove mozilla), and then the same as when you ssh on a remote server for the first time "This answer is by AuthorX , vouched by X, Y ,Z that are not in your chain of trust, explore and accept/deny" ?

Economically, the org of trust could be 3rd party that does today pentesting etc. it could be part of their offering. I'm a company I pay them to audit answers in my domain of interest. And then the community benefits from this ?

Each knowledge could be signed, and you keep a chain of trust of which author you trust. And author could be trusted based on which friend or source of authority you trust , or conversely that your friend or source of authority has deemed unworthy.

We can't on one side ask for people to not make judgment based on statistics and on the other side saying that making a shortcut based statistics is valid.

It's not what I've written.

To clarify, by "dirty work on my pet project" , I meant ,spending times to fix some compilation issues that after 2 hours you told yourself "damnit, I forgot this!" , or when you want to adapt your old python project from python2 to python3.

And I didn't even talked about managment itself.

But , thinking about the big picture, telling claude code to not use this but that. To not overengineer etc. is engineering in my book, and what I've been been doing for the last 8 years at least with more junior engineers.

in a lot of sphere, MCP is still the hype. And it was the hype in even more sphere some month ago.

Because of FOMO a lot of higher up decided that "we must do a MCP to show that we're also part of the cool kids" and to give an answer to their even-higher-up about "What are you doing regarding IA ?"

The project has been approved, a lot of time has been sunk into the project, so nobody wants to admit that "hmmm actually now it's irrelevant our existing API + a skill.md is enough"

I've seen that in at least 4 companies my friends work in, so I would be surprised if it's not something like that here too.

On the contrary claude code, in my experience, has been perfectly able to use `stripe` `gh` and to construct on the fly a figma cli (once instructed to do it).

exactly, as a manager and a sometimes a developer, "vibe-coding" has been looking more and more as my day job (in a good way, it's good to not have to do all the dirty work for your pet projects) and it's all about having the same discipline in term of:

* thinking about the big picture * knowing how you can verify that the code match the big picture.

In both case, somtimes you are happily surprised, sometimes you discover that the things you told 3 times the one writing code to do was still not done.

Thats too vague and drastic, every "show HN" is an ads, for notoriety at least. I would prefer we draw the line at "content pushed by a third party against payment must be displaid only with regard to where it is displaid and must not use information about to whom it is displaid" .

I.e displaying an ads about Sentry on a ads technica page, find . Displaying an ads about hiking equipment on ars techbica because i made a google search abd it is estimated I like that -> not fine. It would kill all the incentive to overtrack the ROI will no more justify the cost.