Claude Opus 5.5 100 HTML Files One hundred self-contained HTML pages made with Claude Opus 5.5: generative art, simulations, instruments, editorial layouts and playful tools, each with the exact prompt that produced it. miaai-lab.github.io This is a really impressive collection of single file sites done by opus 5.5. Miaai-lab even gives you the prompt that she used to make it.
Posts tagged: ai
All posts with the tag "ai"
110 posts
latest post 2026-09-24
Publishing rhythm
dax (@thdxr) on X in the next version of OpenCode we added /btw which is a long awaited feature it lets you ask a quick question without interrupting the current session - i use it to get status updates on long run… X (formerly Twitter) · x.com oooh, excited for this upcoming feature to opencode to be able to gracefully ask a side question without interruption.
Justin Searls @searls /goal is a special command for OpenAI Codex in which it will keep working toward whatever goal you set until it gradually convinces itself that the stated goal is not what you wanted but rather so... justin․searls․co · justin.searls.co LOL, interesting I just heard DHH talk about how we needed goal for a minute blip in history, it did it’s job. Then new models come out trained on our use of it and the models just do it whether you ask for it or not it does not really matter much either way. /goal is a special command for OpenAI Codex in which it will keep working toward whatever goal you set until it gradually convinces itself that the stated goal is not what you wanted but rather some much easier objective was the real goal all along. — @justin
Ai Is To Manufacturing
This is an idea I had today. Using ai to write code is a lot like using CAM software for machining. Default settings plop it in and let it ride is probably decent for a lot of things, but not great for production, you probably want more fine grained tools, higher tolerances, first piece run offs quality gates. A good manufacturing engineer is probably not hand coding g-code, but they know the right gates to pass before sending parts through production.
Hard to argue this so hard here. For me it’s convenience. I work from a terminal most things that are real work get done there so this provide a convenient proximity to real work. If it’s a developer tool for me to use alongside development work I prefer a tui if it can be done in a text interface. Clis are different. Clis provide a great interface into automation, scripting, agent use, interop from two things no one else uses together. Alternatively to the argument for agents making real user interfaces easy I’m going to argue if that’s the case you should have your backend logic hooked into all the interfaces a user could want, CLI, tui, html, rest/http api. I honestly feel like the training data for a good tui just isn’t there and agents default to making bad this.
Hard agree with Theo, terminals suck to use on a phone. Unless you have an attached keyboard they are unusable IMHO. t3 code ad # https://youtu.be/dLhcLqoff6k?t=1354&is=xDCw0PpqH2zkZDou This part of the pitch is fantastic. I think most of the people I talk to can relate to being unsure about when to start work because you want to keep your agents working. My morning process generally includes walking around tmux greeting all of my agents that were working hard last night and unblocking them to get them going for the day. Before even opening team chat, but after checking status pages that #1. My going home routine now has to start about an hour before I leave questioning whether I should start a session or not.
Ai Is A Force Multiplier
Take a moment to think about who it is you want to be. Is this really where you are heading? AI is a force multiplier I’ve heard this many times, notably from @theprimeagen, ex Netflix BTW, who is an excellent engineer that I take a lot of inspiration from. I’ve really started seeing this play out with the various people I work with and myself. Now more than ever we need to consider these personality traits as we try to build out our teams, hire and backfill. We need to think about where we want to see this team and what type of person is really going to get us there, what people we have on the team and what gaps we need to fill. The Prolific Prototyper # The ones who were able to knock out entire projects in a week are able to do this in an afternoon. They are able to ship early and often and get something in the hands of users as fast as they ask for it. Code quality, reliability, observability thrown into the wind, we are lookng for features shipped, actionable use cases implemented…
Ai Is Trained On The Past
When ai tells you “this is 6-8 focused prs” do you ignore, chuckle, laugh. Ya in your training data it might be. by hand it probably was, but realistically I’m going to shove 3 of these at this level into one pr regret my choices later. Decades of pr data no longer makes sense # Introduced on February 23rd 2008 in their 3rd blog post. via
dax (@thdxr.com) so obviously n=1 but anecdotes matter a lot here i gave kimi k3 and sol the same task - simple issue with hovers in the tui being the wrong color sol found and fixed the issue with $0.30 of spend… Bluesky Social · bsky.app So much nuance in model selection its hard to keep up.
oof Mark, this does not feel like it is set to age well. These people in power feel so disconnected from regular people with a job trying to do work.
Programming Still Sucks. — Writing Sorry Peter. — I'm at a birthday party, and while most people here also work in tech, there's always a Guy with a Real Job. You know, a physical job, building some or other thing people need. And... stvn.sh Absolute banger of a post, this is the time we are living in. Explain “are you afraid AI is going to take your job” to a non tech blue collar worker. Broken over promises, greed, and projects mismanaged by leadership who has no idea what the day to day work actually does and how critical it is. I’m not quite in Sara’s position, but I feel something shielded by half of this working deep inside of a non tech part of a non tech company leading a very small rag tag team with get shit done attitude. But I feel it, I see colleagues hit by these blasts.b I get clipped with shrapnel from some of the largest blasts. But nothing as significant as I see many others hit with
Ping 54
I'm regressing back to boomer ai for more plan mode style prompting at home...
It does a decent job at ingesting a repo and coming up with plans before I
start spending precious tokens.
Agent, Prove Yourself
🌱 This post is still growing
Casey had an interesting point here. I think demitri came back with some sense of sanity that its just not how corporations look at employee cost, but I still thought it was a head scratcher. Roughly translated not quoted If the sellers of ai are telling you that your developers are going to be 10x productive, why are they only spending half their salary in tokens? Why not 9x?
I hate how he called out terminal user interfaces as shit… then proved web interfaces to be superior. Damn him. I love working from my terminal, but having ai prove itself through html reports including video, image, metrics, charts, and text is goated. Rethinking yourself has the bottleneck not the orchestrator feels real. Validating the work is hard, theres a shift right now and everyone is trying to figure it out. Lucas’s technique is a little bit of be lazy and tell it to prove itself to you, so as you juggle your 15 agents you have a nice report to read.
This is a really good guide, with quite a few good nuggets. I need to try deleting my AGENTS.md and rebuilding it from scratch more often. I liked how he talked about having agents prove their work and tell them up front how they will be judged. What I didn’t care for so much was the feeling that a lot of the rules go in markdown, thats not a rule, thats a suggestion. Rules should be deterministic. They should be tests and linters that ensure they are followed. Suggestions are good, but dont trust the agents to always follow them. And don’t trust that they wont change your rules, keep them honest.
Write It First, Then Let AI Drive There's a thing that happens when you start using AI coding tools seriously. You assume the best workflow is obvious: let AI generate the first draft, then... Kenneth Reitz · kennethreitz.org Interesting take by Kenneth Reitz. Not quite sure how I feel about it anymore. It kinda hurts, but I’m not sure if code aesthetics matter as much as the product anymore. I cared when I was the one editing, but at this point I’m not doing a lot of edits by hand. Do these aesthetics affect the final products that users use, Not sure. AI makes me sad.
ThePrimeagen (@ThePrimeagen) on X I am slowly coming around to AI assisted programming. I am genuinely trying to codify every rule about programming that I have and using that + several stages to build out small changes. Not s… X (formerly Twitter) · x.com If agents make prime a bit faster, what does that mean for the rest of us mortals?
Uncle Bob Martin (@unclebobmartin) on X AIs aren’t good rule followers. The older the rule in the context window, the less priority it is given. So the best way to enforce the rules is with external tools that communicate failure to th… X (formerly Twitter) · x.com I’ve gotta agree with bob on this one, the first thing I did to my biggest brownfield project I wanted to use agents on BEFORE they did work was a hardened pre-commit.yaml, ci, hardened type checking and linting. SECOND get rid of bad inconsistent patterns, let them replicate consistency, force them to pass checks. Agents will follow all of your markdown suggestions most of the time, enough for you to become complacent if you let it. They are goal seeking, if you put them to a task you thought was possible that is not given your constraints, they will try to find a way given enough tokens. I dont see this ever changing, its one thing that makes them great, it just needs to be kept in check.