ramigb

I just used Astro yesterday for a static website I am deploying to cloudflare pages. I must say I was really impressed by the whole experience! From claude being super fast and diligent to the site structure being “decent” for the tokens and effort spent on it.

If anyone interested here is the source code all done by Opus 5.5 https://github.com/ramigb/esdara

Good my dogecoins were safe! The hacker didn't touch them ... wait .. the hacker didn't touch them?

Yeah that "Pro" usage is a joke! I wish google paid more attention to what the people want! it's a shame I loved Gemini 2.5 and 3 when they first came out they were super amazing!

TLDR "uncensored" so you ask it stuff the vanilla model would refuse and most likely it would comply/answer.

I'd advice caution with abliterated models for various reasons. there was even a couple of days (or weeks I forgot) article here on ynews about how some of these models can get you pawned (https://projectdiscovery.io/research/how-abliterated-models-...)

I swear I have the same question in my head always when I read such statements! I have never once reached 90% that includes everyday usage across multiple repos, artefact generation, device debugging, long running harness work!

I am not saying OP is not telling the truth. I just really want to understand!

If I may add, I don't think people should question their own or others' motives for sharing good deeds and charitable work they have done. In this day and age, we need that motivation and hope in humanity, regardless of the actual intent behind the disclosure.

That's awesome I came from the jev in python thread. is the model shareable? do you have any more writing on this? would love to read more about it! cool demo anyways.

Nice concept but It would've been better if you don't force people to sign in with the auth box always shown I had to delete it from the node tree using chrome devtools. also why not enable WASD keys or even arrow keys to move?

It was only when native English speakers—or those I presumed were—started calling out how bad "GPT/Claude speak" has become that I realized I wasn't actually losing my grip on English as a second language. For a second, I thought, Oh, I learned this language on my own, but it seems I've hit a wall and need to study further. It didn't help that I've also been trying to acquire Swedish as a third language for a while now.

Can you please share, if you are comfortable of course, what did the model(s) mess up? what were you using codex/cc/pi? did the project have a solid agent.md/claude.md? I am genuinely curious whenever someone have such a low success rate with models what is happening because it could be fixed maybe? From my own experience using agents for the past year or so. The rate if I have to guess, is well above 70%. I mainly use claude (opus) on typescript react projects that are well setup with minimal plugins/MCPs!

happy to share more if you are interested.

As I was reading and seeing the video, which is easier to demonstrate as you guessed, I was asking my self the same questions you answered in the "Caveats" section.

I love that you are trying something and you shared it, I relate very much to some parts of the post minus the fatigue part maybe I am it's because I am a very chatty person in general so prompting is not a problem who knows!

I had my own attempts to improve working with AI but to my fault I rarely commit to a project no matter if I wrote it or AI wrote it for me!

I tried this over a year ago https://github.com/ramigb/promachos (before I found out about spec kit and similar solutions) Then I tried this https://github.com/ramigb/groundcheck recently which is to actually help me in the review process specially if there is intent documentation like ADRs or similar.

Your post inspired me to try from a different angle. Thank you.

Same happened to me. Very disappointing, this should be mentioned before the user even authenticates in the onboarding phase of the product asking the user if they have acquired the whitelisting from OpenAI and want to proceed or not! But running for 35+ minutes plus to give such a response is very disappointing and very awkward! Not to mention the lost weekly tokens!

Opencode has a nice pricing with opencode go. Also minimax has a 10 dollars option that gives you 1500 requests every 5 hours!

That's beautiful! I see a .claude folder in your code, I am curious if you've "vibecoded" the whole project or just had claude there for some tasks! not that it matters or takes away from your work but just pure curiosity as someone who enjoys betting on the LLM output XD

yeah me too but npm has the code tab https://www.npmjs.com/package/ezff?activeTab=code

I found that out while working with music models like Suno! I love creating music for my own listening experience as a hobbyist and when I give suno a prompt no matter how well crafted it is the outcome varies from "meh" to "that's good" ... while when I upload semi finished beat I made and prompt it to cover it the results consistently leave me speechless! Could be a bias since the music has a lot of elements I created but this workflow is similar across other generative models for me.

It is scary! my coping mechanism, which I admit is stupid, is to believe no matter what I do as long as I am online they have my data. But you are right most people just give absurd amount of data for willingly.

It becomes even sadder when Google caters to political propaganda of any kind, from any party or country, if the price is right. I wish Google realized how much greater and more beneficial the product and company are to the people who use them than all of that. I am not naïve -I understand they need to profit- but perhaps they are focusing on short term gains while introducing this poor user experience, which will eventually lead to major losses.

I don't think it makes everyone so productive, tbh! If you really know what you are doing and are willing to burn tokens, it will really take your work to the next level—provided you don’t work with a niche product or language that the models weren’t trained on.

If I may use an analogy, it's like what sampling is for music producers. The sample is out there—it’s already a beautiful sample, full of strings and keys, a glorious 8-bar loop. Anyone can grab it, but not every producer can sell it or turn it into a hit.

In the end, every hype train has some truth to it. I highly suggest you give it a shot, if you haven't already. I’m glad I did—it really helped me a lot, and I am (unfortunately, financially) hooked on it.

So your "search engine" uses Google and DuckDuckGo to get results? and you are creating it because "Google sucks"? Am I missing something here?

I came here to say the same thing but I searched if someone else mentioned it. so thank you :D insane nostalgia

I am pretty sure you have a story or two to share after I've read such a paragraph ...

thank you for explaining I am familiar with audio synths never used a video synth, that's awesome.

My first encounter tbh but this is awesome thanks for explaining.

That is why I thought there should be sound but I missed the point it seems as others have commented something to do with modifying the visuals based on a function.

edit: Sorry it seems like I misunderstood the functionality and thought there should be sound. Discard the original comment below.

Original comment: No audio for me on latest chrome. No errors in console.

Now this is how you market a book. cool.

I can be both bored and engaged, don't test me buddy /s

Anything that uses and depends on time synchronization basically. Which is a huge list. from railways to game servers. But again, do they all use these devices or in particular 10-bit counters? I have no idea.

I have no idea if he is or he is not who you are asking him, but it's super impressive that you can recognize a musician name from working on a game. Respect for that sir a lot of musicians would appreciate that.