Feed aggregator

Article URL: https://text.npr.org/nx-s1-5834992

Comments URL: https://news.ycombinator.com/item?id=48284503

Points: 2

# Comments: 0

Article URL: https://reeselevine.github.io/llamas-on-the-web/

Comments URL: https://news.ycombinator.com/item?id=48284498

Points: 5

# Comments: 0

Article URL: https://www.youtube.com/watch?v=1JZnj4eNHXE

Comments URL: https://news.ycombinator.com/item?id=48284495

Points: 2

# Comments: 1

Article URL: https://blog.chrislewis.au/snowboard-kids-2-is-100-decompiled/

Comments URL: https://news.ycombinator.com/item?id=48284494

Points: 2

# Comments: 0

Article URL: https://timomeh.de/posts/software-engineering-wont-be-over

Comments URL: https://news.ycombinator.com/item?id=48284490

Points: 2

# Comments: 0

GSD is great for project management making it possible to run multiple projects at once. My multi-tasking skills can't keep up at the same pace, hence a utility to help me keep track of the projects.

cargo install gsd-meta-manager

TUI for: - GSD milestone and phase progress - git history - open milestones - backlog - browser for the GSD markdown artifacts - tmux support to quickly jump into the project's running claude instance

All feedback, improvements, PR and questions are welcome.

Comments URL: https://news.ycombinator.com/item?id=48284484

Points: 2

# Comments: 0

Article URL: https://www.youtube.com/watch?v=R2m71M4oBNI

Comments URL: https://news.ycombinator.com/item?id=48284458

Points: 1

# Comments: 0

Article URL: https://www.bbc.com/news/articles/c1w22y1n74do

Comments URL: https://news.ycombinator.com/item?id=48284452

Points: 2

# Comments: 0

Article URL: https://www.businessinsider.com/how-mark-zuckerberg-hacked-into-the-harvard-crimson-2010-3

Comments URL: https://news.ycombinator.com/item?id=48284444

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=8zIcP5WlShw

Comments URL: https://news.ycombinator.com/item?id=48284443

Points: 1

# Comments: 0

Article URL: https://coinpusher.io

Comments URL: https://news.ycombinator.com/item?id=48284439

Points: 2

# Comments: 1

Article URL: https://www.yournextventure.co/open-ai-gtm-report

Comments URL: https://news.ycombinator.com/item?id=48284433

Points: 1

# Comments: 1

Article URL: https://third-bit.com/2026/05/20/twelve-ways-to-be-wrong/

Comments URL: https://news.ycombinator.com/item?id=48284430

Points: 1

# Comments: 0

I'm sure many people have some solutions similar to this but I've been using some variation of this since roughly the release of Opus 3 to get higher quality results. Like, significantly higher. So I decided to make it into a more structured package.

Problem: bad decisions and short sighted solutions due to the LLM not having enough context before acting. They'd read one file, or a few segments of a set of files using a super conservative offset and limit, guess about the rest, apply a patch, run a unit test and then tell you with its entire chest that the code is production-ready.

Those bandaids over time became debt, drift, complexity. Unnecessary LOC in a codebase where I find myself wondering is this thing even making me more efficient or should I be in VIM more often and just save myself the API costs (I use OpenCode + OpenRouter and have been known to blast through hundreds of dollars a day in spend using Frontier models).

I found that, for whatever reason, LLMs respond to role-play strongly vs just repeating rules using increasingly alarming markdown context decorators. And so I created a persona for it that is pretty funny when I explain it to someone else but has been really effective.

`monkdev` gives the LLM tools to get enough context before writing any code, it helps you to front-load the context window. This is a more expensive approach, on paper, but the money saved through efficient workflow has definitely worked out for me so I figured I would share it with others.

The main workflow after installing the MCP is just to type `meditate` in a fresh session. If you want to ingest a certain area of the code specifically, `meditate on ` and it will use the tooling provided to aggressively read files. It will confirm the token count and confirm with you before it starts just aggressively `cat`ing your entire project.

It's quite opinionated in terms of structure with Bun and Rust mono-repo projects so if you find it useful fork it and plug in your own preferences. I wanted to avoid making the system prompt too long since I've found that it loses significance in the behavior of the agent if it is over a certain size.

I'm also interested to know if anyone is using something similar or if it can be made to be more efficient.

Comments URL: https://news.ycombinator.com/item?id=48284416

Points: 1

# Comments: 0

Article URL: https://gizmodo.com/theres-at-least-one-job-that-ai-isnt-killing-2000763509

Comments URL: https://news.ycombinator.com/item?id=48284412

Points: 1

# Comments: 0

You can listen to long reads from publications such as Rolling Stone and The Atlantic.

The launch of Ferrari's EV comes as other luxury automakers roll back plans to introduce their own EVs. But public reception is polarized.

Article URL: https://wnmurphy.com/chatgpt-zalgotext-voice-mode-equals-nightmare-fuel/

Comments URL: https://news.ycombinator.com/item?id=48283590

Points: 1

# Comments: 1

Article URL: https://www.youtube.com/watch?v=vM3QucWQygg

Comments URL: https://news.ycombinator.com/item?id=48283568

Points: 1

# Comments: 0