"
Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".
For each frame our pipeline constructs a scene graph with React then
-> layouts elements
-> rasterizes them to a 2d screen
-> diffs that against the previous screen
-> finally uses the diff to generate ANSI sequences to draw
We have a ~16ms frame budget so we have roughly ~5ms to go from the React scene graph to ANSI written.
"
60fps is pathetic for a TUI when most terminals worth their salt are GPU accelerated and displays can be up to 240fps or even more. But let’s be real if I can play Quake at >500 fps they have no excuse.
I don’t know how to phrase this without sounding like an arrogant idiot but seriously: what are people actually programming with agents + worktrees + harnesses + tasks + skills + whatnot? Most workflows I see people adopt involve large amounts of infrastructural fluff only to (more) quickly generate what I (anecdotally) have seen is somewhere between code generation of boilerplatish React/laravel/your-fav-framework components for web or native, and niche toy apps for mostly personal use. My very limited usage of agents has been for scanning large (bloated) codebases to get rid of unused code, meaning time consuming and tedious tasks. But it seems the general trend is that programmers just want faster horses?
You could zoom out a bit and rephrase the question.
Your great-aunt Ida died and left you a consulting team of ten pretty good software engineers. The team's contracts all just ended, so starting tomorrow they'll be idle. Ida said you must run the business for at least two years (fortunately, overhead is already paid for), or forfeit your share of the inheritance. After that you can keep going or liquidate it.
People are just playing around with parallel agents because it looks cool on Twitter. In real prod, 90% of your time isn't spent typing lines of code, it's spent trying to figure out implicit business requirements and debugging undocumented legacy spaghetti. Agents sitting in isolated worktrees are completely useless here - they'll just rapidly and in parallel write code that completely fails to solve the actual business problem
You’re seeing that primarily because it’s what people can show off easily. Side projects they do for fun.
I use all of this stuff daily at work. Normally, I’m working on 2 to 4 features in parallel (so worktrees). This might not be simultaneously, but it’s at least across days or weeks.
Skills, agents, tasks, etc are really about creating repeatability in certain parts of my workflow without needing to be hands on.
Some changes within pre-existing codebases (oh hey, we need feature or mechanism X).
An entirely new internal system with LLM code review, DB migration tracking, time tracking, standups and Teams integration.
A new system that trains neural nets to recognize crops based on Sentinel-2 satellite data (the neural net works okay, mowing and ploughing is harder with a mostly heuristic approach since I don't really have labels).
A new system to migrate somewhere between 1000-2000 forms between proprietary solutions where a team of people have spent a year with limited progress, whereas I'm generating the codegen tool that does most of the work, with the remainder being left up to AI.
A new project linting tool with Go + goja to allow writing rules for validating project stuff in ECMAScript, a bit like ESLint just stack agnostic and can be deployed as a 10 MB executable, to also control stuff like architecture and project conventions that the other tools aren't really geared towards.
Also wrote an OpenAI/Ollama/Claude proxy that allows using on-prem models running on another server through Ollama/llama.cpp and also using AWS Bedrock models when permissions are configured.
Also a bunch of Ansible configuration for stuff like a self-hosted Sentry instance, debugging that piece of shit would be so hard and annoying without something that I can throw logs at (because for some reason they think that having 70 containers running for what should amount to one piece of software is okay).
Also wrote a personal tool that lets me use VLM and Whisper and PySceneDetect and some other stuff to produce EDL so I can take a 3 hour long video and cut it down to 1 hour with LLMs using the transcripts/timestamps (aligned with words, so not too many awkward cuts) that I can then import into DaVinci Resolve for further editing.
Also migrated the apps I host from Contabo VPSes to Proxmox VMs (Hetzner dedicated server from the auction) and went from Docker Swarm + Portainer to pure Docker Compose, also moved from Drone CI to Woodpecker CI and also got rid of the old deprecated Bitnami container images.
Also migrated my homepage from an ancient Ruby and Rails version to more modern ones.
Also wrote a few scripts to replace YOURLS with just an Apache install, the config for which I can automatically append new shortened links to.
I don't even need worktrees or custom skills for most of this, just Claude Code and a subscription, since paying per token would make me go broke.
Yeah perfect example, the main thing I _would_ use multiple agents on is optimizing/benchmarking code, but for that you specifically can't use worktree, you need one agent per machine or they'll taint each other's benchmarks
I stopped looking for fonts after I got comfortable tweaking the metric settings of Iosevka. My current setup exports a set of really compressed cuts (more compressed than Pragmata Pro) which I've always found hard to come by.
You have to realise every single UI up to that point was solid white or grey and unable to access alpha channels. And the fact that they expanded upon this design “language” with the transparent Imac cases made it all cohesive and 2YK hip.
Here is a description of the iteration loop. [0] I'm working on another draft that will be much more polished and have better explanations of the iteration loop.
> There is no proof, just a self-congratulatory word salad with dubious authenticity.
I worked 8 days straight on that and have been working non-stop on the second draft that is much cleaner and safer. I'm a human being. Please don't be mean. If humanity does come to end, it won't be because of AI, it will be because we can't stop being assholes to each other.
I posted a link but don't want to spam HN more than I have.
It is proof-of-concept. Seriously burns some tokens (~80k - ~200k) but doesn't require AI after to scrape and automate a website so if all the people at Browser Use, Browser Base, and every one pounding every website used it, I think, the net benefit would be in the billions. I would recommend using it in isolation. Nonetheless, it works very very well on my machine.
> This type of slop comment is somehow worse than spam.
It sounds like this is along the lines of Firecrawl is trying to do? Or what Plaid has done for banking?
> I think, the net benefit would be in the billions.
I think, you must forgive people if they are somewhat hostile, if not sick and tired of these claims. It’s quite frustrating seeing individuals constantly saying things like this. Meanwhile I don’t think a lot of people are seeing the structural shifts that these claims imply. This is not an original idea. The disruption claim has been made for the past several years in various fields and the goalposts keep getting moved. AI will absolutely change and render some jobs moot even in its current state if Claude/GPT are able to make a profitable business model. If it turns out that Claude is really being subsidized by investors and it turns out that $200/month subscription is really a $5,000/month when Claude has to stand on its on, I’m not sure what’s going to happen.
It’s clear you’ve gotten some good, if expensive use out of AI, but I’m not sure that experience scales or if it will exist in 5 years.
Build steps are realistically speaking inevitable because of minification, tree-shaking, etc. which is not even a big deal these days with tools like esbuild. For a "true" DOM-first component reactive system just use Web Components and any Signals library out there and you're good.
Is this not trivial to get a random person to check stuff for you in exchange for making requests for them (on people they are interested in)? Or is that illegal?
reply