I tried every todo app and ended up with a small stack of flash cards and pen.
When it comes to full on vibe coding (Claude Code with accept all edits), my criteria is whether I will be held responsible for the complexity introduced by the code. When I've been commissioned to write backend APIs,…
The ultralytics/ultralytics repo is pretty beginner friendly (kudos to them for that) but I surmise that it therefore draws a lot of beginner level coders who can't immediately tell that the AI generated "solutions" are…
I've made several contributions to their main repo and the LLM generated mush replies from various core team accounts have been a horror, derailing Issues threads and such. An excellent case study in how not to use LLMs.
This is great! Now I wish there was a wristwatch (Apple Watch face?) that could do this as well.
On the whole I agree, but having read "Reinforcement Learning: An Introduction" by him and Barto, this article comes across as a hardly nuanced self-endorsement of RL as "the inevitable future of AI". Without mentioning…
Proponents of unlimited speed Autobahn could argue: 1. The tourism value: I anecdotally know people visit Germany just for the Autobahn. (See Nürburgring, which is technically an Autobahn) 2. Sale of performance cars:…
Another significant but unnoted design feature is the ability to pass a strap through multiple jerrycans in a row. Essential for mounting them externally to Humvees and MATVs.
I tried every todo app and ended up with a small stack of flash cards and pen.
When it comes to full on vibe coding (Claude Code with accept all edits), my criteria is whether I will be held responsible for the complexity introduced by the code. When I've been commissioned to write backend APIs,…
The ultralytics/ultralytics repo is pretty beginner friendly (kudos to them for that) but I surmise that it therefore draws a lot of beginner level coders who can't immediately tell that the AI generated "solutions" are…
I've made several contributions to their main repo and the LLM generated mush replies from various core team accounts have been a horror, derailing Issues threads and such. An excellent case study in how not to use LLMs.
This is great! Now I wish there was a wristwatch (Apple Watch face?) that could do this as well.
On the whole I agree, but having read "Reinforcement Learning: An Introduction" by him and Barto, this article comes across as a hardly nuanced self-endorsement of RL as "the inevitable future of AI". Without mentioning…
Proponents of unlimited speed Autobahn could argue: 1. The tourism value: I anecdotally know people visit Germany just for the Autobahn. (See Nürburgring, which is technically an Autobahn) 2. Sale of performance cars:…
Another significant but unnoted design feature is the ability to pass a strap through multiple jerrycans in a row. Essential for mounting them externally to Humvees and MATVs.