• 1 Post
  • 15 Comments
Joined 2 years ago
cake
Cake day: July 17th, 2023

help-circle
  • Amen. Context is king, and managing context well is key to proper AI assisted coding. Also, staying accountable for the final output, as you stated in the end.

    Not having good (or any in most cases) context management techniques is like saying your car is slowing you down because you have to push it everywhere you go.

    I use NotebookLM to manage project context, and do scoping, planning and requirement elaboration which gets copied to Jira tickets (similar to what you explained in the first part) . On the coding side I use Claude Code with the Jira MCP. I use the copy-pasting between project and code domains to correct any mistakes AIs might have introduced. We developed a plugin which captures our engineering best practices and instructs the AI agent to discuss every aspect of the implementation and the task breakdown with the developer before writing any code or tests, as well as to keep a local progress tracker file for every ticket which also serves to capture any insights that emerged during the discussion. This file serves as long term memory between chat sessions, and also gets committed for future reference by humans and AI alike. And I always do a thorough self review towards the end.

    I’m convinced beyond doubt coding without modern AI assistants and not gaining experience with them is a mistake. Resist the knee-jerk reaction to downvote comments which give you blueprints to evolve you practice because you have antipathy for AI. I don’t care about the little number at the top of this comment, but I think everyone should start learning and developing new techniques to improve their workflows.





  • The title (click bait as it is) withholds the most important qualifier from the text of which AI we are talking about:

    "“Overall, our model shows that the job loss from AI computer vision, even just within the set of vision tasks, will be smaller than the existing job churn seen in the market […]”

    Sure, computer vision is important for some jobs, but it’s a much smaller subset of jobs that is really deemed protected as claimed by the study. If the knowledge has already been coded to text on the other hand, it’s a different story.










  • I agree, that’s what I’m saying. I used “this” ambiguously, I just realized. I edited “this” to “this comment”, and added another clarifying sentence before the quote.

    Here’s an excerpt from the older article which isn’t paywalled, that I linked in my comment (before the edit):

    "Constructed more than 20 years ago, the turbines at the small Keyenberg wind park are less powerful than modern equivalents, with each producing about 1MW of energy per hour at a wind speed of 15 metres per second, roughly a sixth of the output of a more efficient state of the art turbine.

    Since windfarms in Germany are no longer eligible for subsidies after 20 years in operation, the park would probably have been “repowered” with new technology or wound down even if it were not for the nearby mine.

    Nonetheless, North-Rhine Westphalia’s ministry for economic and energy affairs on Monday urged RWE to abort its plans to dismantle the windfarm.

    “In the current situation, all potential for the use of renewable energy should be exhausted as much as possible and existing turbines should be in operation for as long as possible,” a spokesperson said."