Hacker News: randall

New comment by randall in "Cloudflare acquires Deno"

randall — Fri, 09 Oct 2026 15:14:24 +0000

This is actually awesome news believe it or not. I'm excited b/c i think there's a lot of potential in the world w/ deno's team being on solid footing w/ cloudflare.

I know the runtime is in trouble, but i'm not as worried tbh b/c the principles deno championed are going to keep going.

New comment by randall in "Show HN: Ant – A JavaScript runtime and ecosystem"

randall — Sat, 11 Jul 2026 21:09:50 +0000

+1 to this.

New comment by randall in "Show HN: Ant – A JavaScript runtime and ecosystem"

randall — Sat, 11 Jul 2026 21:09:05 +0000

wow! i’ve been using deno for a long time, and one of my fav features is compiling a binary. i didn’t see anything about that, but might have missed something… do you all plan to support this?

New comment by randall in "Tell HN: Claude 4.7 is ignoring stop hooks"

randall — Fri, 24 Apr 2026 22:23:37 +0000

this isn't strictly true. not that it thinks, but it can reason about the tokens that led to the outcome.

New comment by randall in "Claude Opus 4.7"

randall — Fri, 17 Apr 2026 13:31:10 +0000

this is "you ship your org chart" not ai.

https://en.wikipedia.org/wiki/Conway%27s_law

New comment by randall in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

randall — Sat, 04 Apr 2026 00:05:15 +0000

Does anyone have a link to the "read more"?

New comment by randall in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

randall — Sat, 04 Apr 2026 00:01:43 +0000

exactly. They probably have unsustainable margins on accident.

New comment by randall in "FFmpeg at Meta: Media Processing at Scale"

randall — Mon, 09 Mar 2026 14:53:35 +0000

sweet.

I've been out of the game for a bit but it's great to hear.

New comment by randall in "FFmpeg at Meta: Media Processing at Scale"

randall — Mon, 09 Mar 2026 14:52:30 +0000

This is the least informed take i've ever seen.

I worked at fb, and I'm 100% certain we sponsored VLC and OBS at the time. It would be strange if we didn't sponsor FFMPEG, but regardless (as the article says) we definitely got out of our internal fork and upstreamed a lot of the changes.

I worked on live, and everyone in the entire org worships ffmpeg.

New comment by randall in "OpenAI agrees with Dept. of War to deploy models in their classified network"

randall — Sun, 01 Mar 2026 16:14:00 +0000

even marvel villain thanos was given a plausible motivation.

i don’t think if you actually knew him as a person you’d think this was a reasonable perception.

New comment by randall in "We do not think Anthropic should be designated as a supply chain risk"

randall — Sun, 01 Mar 2026 00:05:54 +0000

same. this is about losing a negotiation and saving face / exacting revenge.

New comment by randall in "OpenAI agrees with Dept. of War to deploy models in their classified network"

randall — Sat, 28 Feb 2026 21:15:02 +0000

i don’t get it. what’s his motive in your view? he literally has no shares in openai.

New comment by randall in "DialUp95 – A 90s inspired nostalgia hit"

randall — Sat, 21 Feb 2026 18:56:39 +0000

I wanted the AOL one to say "Welcome" before "you've got mail!" lol

New comment by randall in "How did Windows 95 get permission to put Weezer video 'Buddy Holly' on the CD?"

randall — Wed, 11 Feb 2026 04:32:26 +0000

The last 3 years of LLM progress, to me, feel like 1994-1998.

New comment by randall in "Students using “humanizer” programs to beat accusations of cheating with AI"

randall — Sat, 31 Jan 2026 19:29:43 +0000

this is like irl cryptographic signatures for content lol

New comment by randall in "Show HN: Gambit, an open-source agent harness for building reliable AI agents"

randall — Mon, 19 Jan 2026 23:19:55 +0000

thanks for the PR! :)

New comment by randall in "Show HN: Gambit, an open-source agent harness for building reliable AI agents"

randall — Mon, 19 Jan 2026 23:18:55 +0000

yaaaaa exactly. You're totally on the same wavelength as me. Let's be friends lol

New comment by randall in "Show HN: Gambit, an open-source agent harness for building reliable AI agents"

randall — Mon, 19 Jan 2026 23:18:10 +0000

once your team comes to a consensus on what PII is, you can roughly guarantee it... especially as models improve.

New comment by randall in "Show HN: Gambit, an open-source agent harness for building reliable AI agents"

randall — Mon, 19 Jan 2026 19:01:54 +0000

So two things.

1/ crypto signing is totally the right way to think about this. 2/ I'm limiting prompt injection by using chain of command: https://model-spec.openai.com/2025-12-18.html#chain_of_comma...

we have a "gambit_init" tool call that is synthetically injected into every call which has the context. Because it's the result of a tool call, it gets injected into layer 6 of the chain of command, so it's less likely to be subject to prompt injections.

Also, relatedly, yes i have thought EXTREMELY deeply about cryptographic primitives to replace HTTP with peer-to-peer webs of trust as the primary units of compute and information.

Imagine being able to authenticate the source of an image using "private blockchains" ala holepunch's hypercore.

New comment by randall in "Show HN: Gambit, an open-source agent harness for building reliable AI agents"

randall — Sun, 18 Jan 2026 23:25:43 +0000

i have a huge theory here that idk when we’ll implement but it has to do with “quorums” and other stuff.

hard to explain… we’ll keep going.