zlacker

[return to "Deno Sandbox"]
1. johnsp+1[view] [source] 2026-02-03 17:33:20
>>johnsp+(OP)
"Over the past year, we’ve seen a shift in what Deno Deploy customers are building: platforms where users generate code with LLMs, and that code runs immediately without review. That code frequently calls LLMs itself, which means it needs API keys and network access.

This isn’t the traditional “run untrusted plugins” problem. It’s deeper: LLM-generated code, calling external APIs with real credentials, without human review. Sandboxing the compute isn’t enough. You need to control network egress and protect secrets from exfiltration.

Deno Sandbox provides both. And when the code is ready, you can deploy it directly to Deno Deploy without rebuilding."

◧◩
2. twosda+X6[view] [source] 2026-02-03 17:58:37
>>johnsp+1
Like the emdash, whenever I read: "this isn't x it's y" my dumb monkey brain goes "THATS AI" regardless if it's true or not.
◧◩◪
3. lucaca+f9[view] [source] 2026-02-03 18:07:12
>>twosda+X6
I can confirm Ryan is a real human :)
◧◩◪◨
4. zamada+pe[view] [source] 2026-02-03 18:26:35
>>lucaca+f9
Is there a chance you could ask Ryan if he had an LLM write/rewrite large parts of this blog post? I don't mind at all if he did or didn't in itself, it's a good and informative post, but I strongly assumed the same while reading the article and if it's truly not LLM writing then it would serve as a super useful indicator about how often I'm wrongly making that assumption.
◧◩◪◨⬒
5. bonsai+ZE[view] [source] 2026-02-03 20:15:49
>>zamada+pe
There are multiple signs of LLM-speak:

> Over the past year, we’ve seen a shift in what Deno Deploy customers are building: platforms where users generate code with LLMs and that code runs immediately without review

This isn't a canonical use of a colon (and the dependent clause isn't even grammatical)!

> This isn’t the traditional “run untrusted plugins” problem. It’s deeper: LLM-generated code, calling external APIs with real credentials, without human review.

Another colon-offset dependent paired with the classic, "This isn't X. It's Y," that we've all grown to recognize.

> Sandboxing the compute isn’t enough. You need to control network egress and protect secrets from exfiltration.

More of the latter—this sort of thing was quite rare outside of a specific rhetorical goal of getting your reader excited about what's to come. LLMs (mis)use it everywhere.

> Deno Sandbox provides both. And when the code is ready, you can deploy it directly to Deno Deploy without rebuilding.

Good writers vary sentence length, but it's also a rhetorical strategy that LLMs use indiscriminately with no dramatic goal or tension to relieve.

'And' at the beginning of sentences is another LLM-tell.

◧◩◪◨⬒⬓
6. jonny_+II[view] [source] 2026-02-03 20:32:40
>>bonsai+ZE
> It’s deeper: LLM-generated code, calling external APIs with real credentials, without human review.

This also follows the rule of 3s, which LLMs love, there ya go.

◧◩◪◨⬒⬓⬔
7. johnfn+RN[view] [source] 2026-02-03 20:57:15
>>jonny_+II
Yeah, I feel like this is really the smoking gun. Because it's not actually deeper? An LLM running untrusted code is not some additional level of security violation above a plugin running untrusted code. I feel like the most annoying part of "It's not X, it's Y" is that agents often say "It's not X, it's (slightly rephrased X)", lol, but it takes like 30 seconds to work that out.
◧◩◪◨⬒⬓⬔⧯
8. jonny_+Oe1[view] [source] 2026-02-03 23:23:01
>>johnfn+RN
It's not just different way of saying something, it's a whole new way to express an idea.
[go to top]