HNHacker News
TopNewBestAskShowJobs

mewpmewp2

3,684 karma · joined November 13, 2019

submissionscomments
mewpmewp2··on Why the heck are we still using Markdown?
Yes fully agreed, markdown is going to win by far just because of tokens and AI. The only thing I think right now that should be advanced, is plugins/custom components for markdown, like .mdx, etc token efficient ways of visualizing things in various ways, or custom interactive components, etc.
mewpmewp2··on The Claude Code Leak
On the other hand, consider if they took their time to make sure that quality is super good, did not mainly vibe code it, then they would have never become as popular as quickly as they did and would have been outcompeted by other llm providers. They only got so popular because they released Claude Code so quickly it was the most productive thing for everyone to use at that time.

And frankly at that point Claude Code as software doesn't matter anymore. It is about their models, they could throw it away, rewrite from scratch, etc, it wouldn't be a big deal.

Claude Code as a harness was never likely going to be for 10 years, because there would be so many of these harnesses, all different, the direction may change, etc.

As I understand someone internally quickly vibecoded for themselves only as a productivity tool, and then they realized internally how productive it can be, they decided to release it and people found it so productive they got hugely popular now thanks to that while otherwise would have been eaten out by OpenAI.

Also if requirements for this had to came from product it would have never even happened in the first place. As it was engineer trying to optimize their own workflow.

The only reason they decided to hide source code is to delay competitors imo and it wasn't related to security or anything, but by now OpenCode etc are objectively better tools anyway.

mewpmewp2··on Axios compromised on NPM – Malicious versions drop remote access trojan
Hopefully "es" will have Siesta support too.
mewpmewp2··on We rewrote JSONata with AI in a day, saved $500k/year
The customer could be on the fence between you and a competitor and this customer could be potentially paying 10x more than all your existing customers together. It could make or break your company. They would go to the competitor immediately if you make it complicated for them and have delays with the setup. What do you do then?
mewpmewp2··on We rewrote JSONata with AI in a day, saved $500k/year
What if you are about to get a potentially really high paying customer, but they might go elsewhere unless you deliver X feature immediately and it is so much quicker to do it with the JS script?
mewpmewp2··on We rewrote JSONata with AI in a day, saved $500k/year
But what is your income? How important it is to address should be compared to that and current profits too if any, and whether you have to be profitable right now.
mewpmewp2··on We rewrote JSONata with AI in a day, saved $500k/year
Yeah that checks out to me, 1 hour of active Claude Code usage has been around $50 per hour for me.
mewpmewp2··on The 100 hour gap between a vibecoded prototype and a working product
I would say that if AI has to make decisions about picking between framework or constructs irrelevant to the domain at hand, it feels to me like you are not using the AI correctly.
mewpmewp2··on Agents that run while I sleep
I think tests in general are good, just not TDD as it forces you to what I think bad and narrow paradigm of thinking. I think e.g. it is better that I build the thing, then get to 90%+ coverage once I am sure this is what I would also ship.
mewpmewp2··on Agents that run while I sleep
I think there is a difference whether you do TDD or write tests after the fact to avoid regression. TDD can only work decently if you already know your specs very well, but not so much when you still need to figure them out, and need to build something actual to be able to figure it out.
mewpmewp2··on Agents that run while I sleep
You can build those things in modern frameworks, it will just be more headache and will feel outdated in 6 months.
mewpmewp2··on Agents that run while I sleep
I am not laughing about PHP. To this very day many of my best projects are built on PHP. And while last 7 years I have spent in full stack JavaScript/TypeScript environment it has never produced the same things I was actually able to do with PHP.

I actually feel that things I built 15 years ago in PHP were better than anything I am trying to achieve with modern things that gets outdated every 6 months.

mewpmewp2··on We are changing our developer productivity experiment design
Definitely need to stop squashing commits if that is the case! But no, seriously tracking git commit counts is absolutely ridiculous. Maybe you can have AI autonomously work on useless documentation that no one will read, with 1 commit per 100 lines of markdown?
mewpmewp2··on A psychedelic medicine performs well against depression
I think there's simply so much value in being able to see the same thing in so many different perspectives that you never have considered possible at all in your life before.
mewpmewp2··on IronClaw: a Rust-based clawd that runs tools in isolated WASM sandboxes
It is just ks is same as x.

I mean honestly if you pronounce the name it is going to sound like that outside eastern europe too, so I am not sure about that name choice at all. Intentional?

Looking at the website it looks like a vibecoded joke, but what do I know.

mewpmewp2··on Claude Code is being dumbed down?
I am not paying this myself, but the place I work at is definitely paying around 2k a month for my Claude Code usage. I pay 2 x 200, for my personal projects.

I think personal subs are subsidized while corporate ones definitely not. I have CC for my personal projects running 16h a day with multiple instances, but work CC still racks way higher bills with less usage. If I had to guess my work CC is using 4x as little for 5x the cost so at least 20x difference.

I am not going to say it has 10xed or whatever with my productivity, but I would have never ever in that timeframe built all those things that I have now.

mewpmewp2··on Why I Joined OpenAI
[flagged]
mewpmewp2··on Hypnosis with Aphantasia
I do think that my body is tensed up, but I think it is constantly tensed up. Or at least others say I am tensed up. I wonder if I have this constant tension then and I feel this constant sense of dread and anxiety and that is why I can't recognize change in my body, or emotions having physical meaning because it is just constant low grade tension?

But the tension is everywhere not necesseraily pointed to a specific location.

Like I don't ever feel what I think is "good". I feel like there is always something that I should be doing, solving some problem that is on back of my mind. I can try to make myself forget about the problems I have to solve temporarily, but mostly it doesn't work.

But it is always the same, constant feeling of pressure and inability to relax, while my therapist seems to assume it comes on and off and in a specific body part.

mewpmewp2··on Hypnosis with Aphantasia
So if my heart rate stays the same even though I feel anxious I am not anxious? I am thinking I am anxious and that I don't feel good, but I don't really notice any physical symptoms.

E.g. I am worried about upcoming deadlines, or whether I am going to make it, maybe it is not a direct fight or flight anxiety though, but what is it then, just stress?

mewpmewp2··on Hypnosis with Aphantasia
Not related to article ncessarily, but more so to processing differences. One more thing that I think might be similar in fashion. In therapy I will say what I am feeling, e.g. anxiety, frustration or whatever. But then I am asked "where" in my body am I feeling it. And I have no clue what to answer. I don't think my feelings are felt in random body parts. Although supposedly this is not pseudoscience and people feel things in their bodyparts? I wonder if this is just another processing difference I have compared to other people. And my therapist kept asking even though I could not answer. I started to doubt if I have emotions in the first place.

I wonder if people process and feel what they think are same emotions in very different ways? I usually am externally quite unreactive though, but I didn't think I don't feel emotions actually?

Or maybe I do feel something in my bodyparts, but I am just unable to identify or recognize it? If I am frustrated or anxious and I focus on my brain, maybe I can kind of tell there is tightness? But then I could focus on other bodyparts, and I can also think that maybe there is chest heaviness? But then I can focus on my feet and think ok even my feet can feel weird, but is it because I am focusing on them and thinking there should be something?

mewpmewp2··on Hypnosis with Aphantasia
I think it is the case where you just assume that people are embellishing or being metaphorical about those things and you just refuse to consider for a moment that they are actually seeing something. But it does give this thought that why do people like to embellish or be metaphorical so much? I guess the answer is that they are not!
mewpmewp2··on Hypnosis with Aphantasia
I get my ideas completely from inner monologue. But my ideas are mostly related to developing automated systems etc, I don't really need imagery for that, although I think I need to sense some sort of graphs or how things work together on the higher level.
mewpmewp2··on Hypnosis with Aphantasia
I don't see any images, but I have trouble sleeping because of my inner monologue or not feeling calm etc.
mewpmewp2··on Claude Code On-the-Go
I've got the per PR env with CI/CD setup working now! I still have to wait until tomorrow before I can use Claude Code (or I could use the API token, but I've already spent so much on everything).

I do have ArgoCD too now, right now Github self hosted permanent runners work, so I'll look to switch I think after some time.

I have to understand your browser usecase better. I'm using playwright for automated browser/e2e right now?

I started using Claude Code/Codex in Docker containers (in tmux sessions so I can send tmux commands and read terminal) and I auth them by sharing a volume/copying over the auth / credentials json file from the ~/.claude/ ~/.codex dir. Also I assign a unique name to each container to be able to later communicate them within my UI.

Does this solve the subscription problem for you if I understand the problem correctly?

mewpmewp2··on Claude Code On-the-Go
I ran out of Claude Code sub (I have the $200), so I tried setting this up with Codex. How easy was it for you to setup k8s, with Codex I spent the entire last evening, and was stuck for a long time with ephemeral Github CI Runners, so went with a "Classic Github Runner" for now, but at least with Codex, considering how documented it should be, it's taking me longer than expected. How was the experience for you, and any tips? Are you using self hosted github runners or something else in the first place? Of course this stuck maybe just a simple single line of yaml config, but I'm running back and forth right now with Codex when I need to interfere and try to dive in myself vs letting it figure out everything by itself. Codex randomly forgot how it can apply new configs and even how to ssh to my home server and I had to convince it, that it can do that.

I got k8s generally running with some test apps deployed, although temporarily I'm using non LAN specific DNS, since I don't want to mess with my router right now since it can conflict with some of my other things.

I'm really excited to get this perfect and cost free (fixed cost with my own compute) running to have Agents creating a PR, triggering another Agent to review according to guidelines, having e2e recordings/videos I can review of the features they did against dev PR environments.

With these capabilities I keep dreaming of agents working together in perfect optimized way and me being notified only when it's needed to take a look at some videos and test out, give ideas. I have tons of things I want to build...

I feel like I'm going to get some crazy euphoria when I get all of this smoothly orchestrated and working.

mewpmewp2··on Claude Code On-the-Go
These are all some excellent ideas, I need to setup these things asap since I've been going back and forth on having more homelab vs cloud providers, but I'm only hearing about tailscale right now so I got to go for it. Cloud providers all of sudden becoming costly just for my side projects and/or not providing the exact PR environments like I would like etc. I've been wasting so much time on trying to automate AI Agents vs cloud providers with limited conf.. It would be great if AI Agents can just write the config for all deployments, pipelines, standards, without me having to go to any UI to tweak things manually etc.

Even with GitHub CI now all of sudden it wasted $50 on few days of CI actions. Should have everything run on my home server. But I think I may need more powerful home server, I have a cheap Dell refurbished one now.

I don't want to ever have to touch a UI again (except in places like Hackernews or the like) and the ones I specially built (read: vibecoded) for myself.

mewpmewp2··on Claude Code On-the-Go
What kind of homelab do you have? And how do you do routing, do you have some sort of DNS setup too?
mewpmewp2··on Claude Code On-the-Go
What hosting do you use for automatic per PR dev environments?
mewpmewp2··on Show HN: Vibium – Browser automation for AI and humans, by Selenium's creator
I guess the issue is that real world does smell terribly. I wish I could just have the perfect World like my side projects always have, but not the case with the commercial ones making money.
mewpmewp2··on Show HN: Turn raw HTML into production-ready images for free
Won't you need to install extra libraries for these?
← PreviousPage 5 of 34Next →