"I cancelled my #Claudecode subscription. I have a tendency to fixate on things and overdo it. Most of the time I can manage and keep things mostly under control, but this has the potential to do #realdamage. Worst of all, I wouldn't have anything to show for it at the end. #Codingagents have a way to turn your brain off: no learning, no big picture, just #prompting until it does your bidding. If I ever need such a tool, I'll run it locally with one of the open-source coding models. I'll use #LLMs for code like people use Shein for clothes. They both have terrible impact on communities and the environment, the comparison seemed fitting."

https://tresbien.tech/blog/and-now-im-recovering/

"I cancelled my #Claudecode subscription. I have a tendency to fixate on things and overdo it. Most of the time I can manage and keep things mostly under control, but this has the potential to do #realdamage. Worst of all, I wouldn't have anything to show for it at the end. #Codingagents have a way to turn your brain off: no learning, no big picture, just #prompting until it does your bidding. If I ever need such a tool, I'll run it locally with one of the open-source coding models. I'll use #LLMs for code like people use Shein for clothes. They both have terrible impact on communities and the environment, the comparison seemed fitting."

https://tresbien.tech/blog/and-now-im-recovering/

AI Prompting is almost never a One Shot and you're done. #AI #Prompting

Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022)

https://arxiv.org/abs/2211.12588

#HackerNews #ProgramOfThought #Prompting #ChainOfThought #AIResearch #MachineLearning #2022Study

Stop using prompt checklists. They failed 20 years ago, and they're failing now.

When the internet arrived, critical reading checklists (like CRAAP) became obsolete because humans are unlikely to apply static rules to dynamic content.

Same story with AI. Sequential optimization (conversation) crushes single-shot prompts.

The future isn't better prompts. It's better dialogue.

https://wiobyrne.com/weve-been-thinking-about-prompts-all-wrong/

#AIChat #FutureofWork #Prompting

Honda: 2 years of ml vs 1 month of prompting - heres what we learned

https://www.levs.fyi/blog/2-years-of-ml-vs-1-month-of-prompting/

#HackerNews #Honda #ml #prompting #machinelearning #AI #insights