Dean Laverty

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.

LiveFPL’s new Rank page is now live! Explore it during the games today, I’m hoping it will be smoother and faster than any LiveFPL experience you’ve had before. Hopefully! And I really appreciate your patience if you spot any bugs 🙏 Besides the smoother server experience, dark mode, and language support, there are a bunch of new additions: 1- What-If is back (like in the mobile app) so you can add/remove events and see your hypothetical rank. 2- Captains and chips breakdown for every rank tier. 3- The top 5 events that impacted your rank this GW. 4- Visuals showing where your rank sits between milestones, how many players you have left vs the field, captain points, etc. 5- A live chart of your rank over time as events move it up and down, this one is very special to me and deserves its own tweet. 6- Detailed rank impact data when you click any player, anywhere. 7- Live Games/Bonus/Defcon/Points/EO/Feed have all improved …and more. Explore and I hope that, after giving it some time, you’ll enjoy it and forget the old version (I know every change has inertia)