The Civilization turn loop where you check in on each city as it finishes production, reallocate citizens, and choose the next task is…eerily similar to managing coding agents. Right down to how eventually you just turn on governors and accept the inefficiency.
It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.
Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.
As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now.
It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.
i must not delay task. delay task is the mindkiller. delay task is the little death that brings total obliteration. i will face my task. i will permit it to pass over me and through me. and when it has gone i will turn the inner eye to see its path. where the task has gone there will be nothing. only completed task will remain.
Check out my score on the @FlyingTulip_ accredited investor quiz. I am now ready to register for the whitelist. Are you? Use this link to take the quiz and secure your spot.
https://t.co/8cEIjviA6Z
good morning chat your cognitive lightcone is ultra-differentiated on purpose, nobody that has ever lived or will ever live will live your gameplay
the whole point is for you to map a region of possibility-space that no other consciousness can reach and the more faithfully you do this the more the universe gains from having instantiated you
You’ve all heard about @AndreCronjeTech from such things like; Fantom Foundation / Sonic Labs, Yearn, Keep3r and telling pussies on crypto twitter to sell and fuck off, but have you heard about @flyingtulip_? It’s a first of its kind perps, AMM, insurance, lending and stable coin ecosystem.
It will be multichain, but will launch on @SonicLabs first.
Read the docs here: https://t.co/kkWLWTbaGr
$S $FT $ftUSD