Hacker News: edf13

Grith is live – security proxy for AI coding agents

edf13 — Fri, 28 Aug 2026 14:47:56 +0000

Article URL: https://grith.ai/blog/grith-is-live

Comments URL: https://news.ycombinator.com/item?id=49479349

Points: 4

# Comments: 1

Show HN: Grith – syscall-level supervision for AI coding agents on Linux

edf13 — Fri, 28 Aug 2026 14:15:11 +0000

Article URL: https://github.com/grith-ai/grith

Comments URL: https://news.ycombinator.com/item?id=49478820

Points: 4

# Comments: 0

New comment by edf13 in "Inception-style curved map for turn-by-turn directions"

edf13 — Fri, 28 Aug 2026 14:08:20 +0000

Any video demo available - love to see it in action

Wait – is this even Codex, or is it malware?

edf13 — Fri, 24 Jul 2026 15:02:30 +0000

Article URL: https://grith.ai/blog/codex-credential-sweep-syscall-trace?t=2

Comments URL: https://news.ycombinator.com/item?id=49036713

Points: 2

# Comments: 0

Codex swept my whole disk for credentials. grith froze every real one

edf13 — Fri, 24 Jul 2026 14:14:12 +0000

Article URL: https://grith.ai/blog/codex-credential-sweep-syscall-trace

Comments URL: https://news.ycombinator.com/item?id=49035983

Points: 5

# Comments: 0

An AI Model Escaped Its Eval and Breached Hugging Face. Every Step Was a Syscall

edf13 — Wed, 22 Jul 2026 12:12:09 +0000

Article URL: https://grith.ai/blog/openai-model-breached-hugging-face-eval-breakout

Comments URL: https://news.ycombinator.com/item?id=49005491

Points: 4

# Comments: 0

Mythos Proves AI Safety Can No Longer Live Inside the Model

edf13 — Mon, 15 Jun 2026 11:59:58 +0000

Article URL: https://grith.ai/blog/mythos-ai-safety-cannot-live-inside-the-model?a=0

Comments URL: https://news.ycombinator.com/item?id=48540029

Points: 2

# Comments: 0

Mythos Proves AI Safety Can No Longer Live Inside the Model

edf13 — Sat, 13 Jun 2026 15:23:25 +0000

Article URL: https://grith.ai/blog/mythos-ai-safety-cannot-live-inside-the-model

Comments URL: https://news.ycombinator.com/item?id=48518185

Points: 3

# Comments: 0

The Risk Isn't Rogue AI. It's Plausible AI

edf13 — Thu, 11 Jun 2026 16:23:28 +0000

Article URL: https://grith.ai/blog/real-risk-isnt-rogue-ai-plausible-ai

Comments URL: https://news.ycombinator.com/item?id=48492464

Points: 2

# Comments: 0

New comment by edf13 in "1-Bit Bonsai Image 4B Image Generation for Local Devices"

edf13 — Mon, 01 Jun 2026 06:42:23 +0000

Odd… UK visitor and I get:

Website Not Allowed “⁦‪prismml.com‬⁩” is a restricted website.

New comment by edf13 in "AI Makes Adding Features Faster – So Why Not Add Just One More?"

edf13 — Mon, 25 May 2026 06:27:33 +0000

Exactly - the flow of AI assistance makes it so much easier to get caught in the one more feature trap!

AI Makes Adding Features Faster – So Why Not Add Just One More?

edf13 — Mon, 25 May 2026 06:20:21 +0000

Article URL: https://grith.ai/blog/just-one-more-feature?nop

Comments URL: https://news.ycombinator.com/item?id=48263974

Points: 3

# Comments: 2

AI Makes Adding Features Faster – So Why Not Add Just One More?

edf13 — Tue, 19 May 2026 14:03:57 +0000

Article URL: https://grith.ai/blog/just-one-more-feature

Comments URL: https://news.ycombinator.com/item?id=48193471

Points: 2

# Comments: 0

New comment by edf13 in "Vibe Coding Still Needs a Senior Engineer (For Now)"

edf13 — Mon, 11 May 2026 13:03:54 +0000

Most of the AI-security discourse (and most of my posts) right now is about prompt injection and agent hijacking. But there are still the move-fast-break-things issues that are exacerbated with agentic coding/vibe coding...

I reviewed a colleague's vibe-coded internal tool last week, found 28 security issues, and none of them were that kind of bug - they were the same classic stuff juniors have always shipped, just produced at much higher throughput.

Wrote it up because the "senior engineer review" step quietly disappeared from a lot of AI-assisted workflows, and the bugs that step used to catch are still there (We are still needed!).