Hacker Newsnew | past | comments | ask | show | jobs | submit | beoberha's commentslogin

Beads is amazing. It’s such a simple concept but elevates agentic coding to another levels

Yep, as a manager, I am explaining this conundrum often. You can be a rockstar SDE 2 or senior, but not be ready for a promotion because you aren’t leading enough.

I have a feeling most of these folks are talking about personal projects or work on relatively small products. I have a good amount of personal projects that I haven’t written a line of code for. After bootstrapping an MVP, I can almost entirely drive by having Claude pick up GitHub issues. They’re small codebases though.

My day job is mostly a gigantic codebases that seem to still choke the best models. Also there’s zero way I’d be allowed to tailscale to my work computer from my phone.


It’s a fast moving field. People aren’t coming up with new ideas to be performative. They see issues with the state of the art and make something that may or may not advance things forward. MCP is huge for getting agents to do things in the “real world”. However, it’s costly! Skills is a cheap way to fill that gap for many cases. People are finding immediate value in both of these. Try not to be so pessimistic.


It's not pessimism, but actual compatibility issues

like deno vs npm package ecosystems that didn't work together for many years

There are multiple AGENTS vs CLAUDE vs .github/instructions; skills vs commands; ... intermixed and inconsistent concepts, all out in the wild

When I work on a project, do all the files align? If I work in an org, where developers have agent choice, how many of these instructions and skills "distros" do I need to put (pollute?) my repo with?


Skills have been really helpful in my team as we've been encoding tribal knowledge into something that other developers can easily take advantage of. For example, our backend architecture has these hidden patterns, that once encoding in a skill, can be followed by full stack devs doing work there, saving a ton of time in coding and PR review.

We then hit the problem of how to best share these and keep them up to date, especially with multiple repositories. It led us to build sx - https://github.com/sleuth-io/sx, a package manager for AI tools.


Depending on your workflow, none.

While I do agentic development in personal projects a lot at this point, at work it's super rare beyond quick lookups to things I should already know but can't be arsed to remember exactly (like writing a one-off SQL scripts which does batching mutations and similar)


I’m incredibly biased (I work at Microsoft) but I love Teams. It’s a great meeting app and a great chat app. It blows my mind that there are companies that have totally separate apps for each (Zoom/Slack).


It’s more incredible to me that Microsoft has different versions of teams that don’t work with each other, but are named the same thing, and that the home version of teams that doesn’t work with enterprise teams comes forcibly bundled with an pro or enterprise os.


It's so fucking bizarre that there are multiple versions of the same thing, that are called the same thing but aren't the same thing!


Teams is the only meeting app where I am usually late because it doesn't just let me join my meeting. Zoom will never lock up letting you join a meeting because someone decided you need to reauthenticate Teams regularly.

This would be understandable if it happened quickly but normally Teams has a seizure for a minute or two when you try to join the call and then you get told to sign in. Whoever allowed this behavior to ship should be fired out a cannon... when I click join a call, absolutely nothing should stop me from joining a call.

In fairness this might not be explicitly Teams' fault. It's built on top of a terrible authentication platform which also seems to be down at least four or five days a year. 365 is one of those things that could not exist if not for the incredible monopoly Microsoft has over Excel.


It's gotten so much better recently, and I used to be a Teams hater.


I definitely agree with you, but it’s probably a little apples and oranges. MCP server is a one stop shop for discovering “tools”. To leverage a CLI tool “from scratch”, your agent has to do a web search to find if a CLI tool even exists, figure out how to install it, install it. Not saying those are impossible, but it’s way less automated and “deterministic” than what MCP provides.


I don't quite follow your meaning. Are you referring to an MCP registry of some kind, that the agent would operate itself to discover and install new tools? I would say that is a separate concern from the tool form factor itself. Also, there are CLI-focused solutions to this as well (e.g. brew, npm).


Curious why pgduck_server is a totally separate process?


The README explains it:

> This separation also avoids the threading and memory-safety limitations that would arise from embedding DuckDB directly inside the Postgres process, which is designed around process isolation rather than multi-threaded execution. Moreover, it lets us interact with the query engine directly by connecting to it using standard Postgres clients.


What has been pointed out from the README; also:

- Separation of concerns, since with a single external process we can share object store caches without complicated locking dances between multiple processes. - Memory limits are easier to reason about with a single external process. - Postgres backends end up being more robust, as you can restart the pgduck_server process separately.


from the README:

> This separation also avoids the threading and memory-safety limitations that would arise from embedding DuckDB directly inside the Postgres process, which is designed around process isolation rather than multi-threaded execution. Moreover, it lets us interact with the query engine directly by connecting to it using standard Postgres clients.


Thanks! Didn’t scroll down far enough


Sam is a great twitter follow


thank you


Off-topic, but you have a typo on your pricing page: "high-availablity"


A lot of reductive anti-cloud stuff gets posted here, but this might be the granddaddy of them all.


Former players being hired as head coaches without much other coaching experience is fairly common in the NBA.


Yes, but in this case the blazers head office said they were going to search for a coach, and they also took input from Dame on what coaches he thought would be good for the team.

They didn't do any search at all, and just went straight to hiring Chauncey.

This partially contributed to Dame leaving - it also didn't help that Chauncey and Dame didn't quite get along (and also deciding to bench him in the last 10 games of the season to tank).

I'm honestly fine with players being hired as head coaches. Before looking into it I thought it was totally fine with Chauncey, especially given his track record as a leader on the Pistons and being a phenomenal classic point guard.

The main issue for me is just telling people you're going to do a search... and then not doing it.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: