Viewing profile — drdexebtjl
drdexebtjl
HN member- Joined
- Tue, Jun 16, 2026, 1:02 AM UTC
- HN karma
- 563
- Public activity
- 261 items
- HN profile
- View on Hacker News ↗
About drdexebtjl
No profile information was provided.
Recent public activity
-
comment
Comment #49217294
I was replacing the factory OS from a NAS and asked Sol to do an inventory on the running system over SSH, so that I could replicate any hardware compatibility quirks and whatnot. …
- comment
-
comment
Comment #49199747
Acceleration is not very important at a high enough level because you can mini-turbo up to top speed when you get hit.
-
comment
Comment #49199691
Competitive players (from Mario Kart in particular) are doing this type of data mining and analysis ever since the game releases, and sharing them in tightly knit communities. The …
-
comment
Comment #49198357
The fact that app piracy is more prevalent on Android has nothing to do with technical differences between iOS and Android side loading, and everything to do with the markets in wh…
-
comment
Comment #49196956
Is it because the sandbox is bad and does not perfectly simulate the computing environment of a real device? Because to me it sounds like a cat and mouse game that Google and banki…
-
comment
Comment #49196876
They can’t force someone to make a product, but they can force someone to choose between making a product or exiting the EU market. In practice they’re the same thing.
-
comment
Comment #49196785
Of course you can. How do you think developers test their apps?
-
comment
Comment #49189031
Letting them read my conversations is okay. Systematically reconstructing a timeline of every keystroke that went into a project, then immortalizing this timeline into a VCS, that’…
-
comment
Comment #49188387
Don’t worry, Zed (or another company in their VC backers’ portfolios) will helpfully sell you inference to filter through that noise!
-
comment
Comment #49188128
This makes me uncomfortable. Maybe I’m pessimistic, but I think this just gives micro-managers the data they need to micro-manage you. It invites people to scrutinize the process, …
-
comment
Comment #49187727
Someone in the forum thread reports it runs on their Pi. I don’t see why it couldn’t work, since Debian runs fine on these SBCs. Maybe they mean there’s no enterprise support, but …
-
comment
Comment #49186119
Also apparently they will randomly terminate your instances if they think you’re not using them enough. Or if you’re using them too much. Can’t tell, it’s not transparent. Also, th…
-
comment
Comment #49184120
It can’t possibly be more expensive than doing equivalent work using context instead of RAM and inference instead of CPU. Unless we’ve got the wrong balance of compute availability…
-
comment
Comment #49183680
It used to be partially because building tools is fun. Often more fun than building whatever the company actually needs. But now it’s not that fun. LLMs need to say stuff like “you…
-
comment
Comment #49183096
REST has issues if you limit yourself to think of the “resources” as your domain entities. If you have a long running search, the resource is the search. Create a search. Fetch sea…
-
comment
Comment #49182916
OpenAPI 3.0 has auth. You can turn OpenAPI specs into tool calls just as well, without giving your agents access to call curl and without leaking credentials. The problem is often …
-
comment
Comment #49182568
> CLI tools don’t have standardized auth EPERM, POSIX ACLs and execute bits. > CLI tools need to access your secrets in your .env They can access whichever secret store you want. T…
-
comment
Comment #49179514
I think OpenAPI does all you mentioned in your comment too. Maybe MCP is more strict, in the sense that it requires natural-language descriptions, which are optional in OpenAPI, bu…
-
comment
Comment #49179331
In the same vein, if we do evolve MCP to support composable tool calls and more tools, eventually we’ll reimplement Bash. The difference is that we already have Bash :)
-
comment
Comment #49179281
They’re not the same thing under a different wire protocol! An MCP tool call that returns the top N spenders puts the result in the agent’s context window. A CLI tool call on the o…
-
comment
Comment #49179124
Because there’s probably a tool call for web search, and a tool call for arbitrary code. There’s no discovery for the CLI tools it has available unless it has already chosen to run…
-
comment
Comment #49179077
Why can’t the LLM you’re talking to on the web have access to your CLI tools? When you talk to an LLM on the web, the harnesses spin up a fresh environment (I would hope it’s a VM……
-
comment
Comment #49179013
At that point you would add a `your-service-cli list-customers --order-by=spent` command, which would also be useful to humans and scripts, as opposed to an MCP tool call, which is…
-
comment
Comment #49178961
I don’t think the “just use a CLI” crowd really are assuming you’re a developer in a coding harness. All of those use cases you mentioned benefit from the agent having access to a …