Hacker News: gb2d_hn

The skills I think we might gain (AI)

gb2d_hn — Wed, 24 Jun 2026 19:19:33 +0000

Article URL: https://blog.g9n.com/the-skills-i-think-we-might-gain-ai#decision-making-at-pace

Comments URL: https://news.ycombinator.com/item?id=48664505

Points: 2

# Comments: 0

New comment by gb2d_hn in "Computer use in Gemini 3.5 Flash"

gb2d_hn — Wed, 24 Jun 2026 18:31:17 +0000

It's honest - people who know what they are looking at will take speed and token costs into account. I don't use Gemini 3.5 for coding, but I use it as something in between a search engine and agent.

New comment by gb2d_hn in "Show HN: Oak – Git alternative designed for agents"

gb2d_hn — Tue, 23 Jun 2026 06:52:13 +0000

Git has worktrees, which provide a means of creating branch linked physical working directories. I built in UI assistance for creating worktress associated with the agent session in https://www.agentkanban.io (an agent integrated kanban board for use with copilot / claude and vs code). I agree, I would rather try and make use of a tool that the agent is already familiar with, unless it's missing features that the agent needs to achieve its goal (which git is not)

New comment by gb2d_hn in "Code duplication is far cheaper than the wrong abstraction (2016)"

gb2d_hn — Sun, 21 Jun 2026 17:24:13 +0000

It's made me wonder the same, but most LLM generated codebases haven't been around long enough to judge maintainability. I have noticed issues in some of my more LLM heavy code when I expect a change to be replicated in multiple areas, assuming common code / styling was reused, only to find it wasn't. It's for that reason I can't use LLMs for client codebases without heavy scrutiny of every line generated (for my own hobby projects I'm a lot more lenient)

New comment by gb2d_hn in "Code duplication is far cheaper than the wrong abstraction (2016)"

gb2d_hn — Sun, 21 Jun 2026 17:20:40 +0000

Interface over inheritance is the paradigm I try and stick to. I'd rather maintain orthogonal code than code with overuse of inheritance because of over adherence to DRY.

New comment by gb2d_hn in "Has AI already killed self-help nonfiction books?"

gb2d_hn — Wed, 17 Jun 2026 11:08:39 +0000

Self help books are the most filler heavy books. They often have a useful point, but they just don't need to be a book much of the time. This is unfortunate for the authors who have often put significant time into producing the information. Technical manuals typically need all of their content due to the level of detail, and novels need all of their content because it's the content which provides enjoyment. For self help, people just want to know what they need to do to make their lives better? Maybe the work has to move into academia where we have existing infrastructure for rewarding non profitable work for the good of the public?

New comment by gb2d_hn in "Running local models is good now"

gb2d_hn — Wed, 17 Jun 2026 09:40:09 +0000

For me it's about the value of my time. I think that it's important that we have open models, but for getting real work done, my time is too valuable to waste it on subpar results or additional agent management when a max plan covers all the use I need. It's not worth quibbling over. If the cost / benefit ratio changes, I'll be looking harder at local set ups, but not at the moment.