Hacker News: yruzin

Show HN: Aplexica – resume a Claude Code conversation in Codex, and back

yruzin — Wed, 16 Sep 2026 14:25:31 +0000

Article URL: https://github.com/Aplexica/Aplexica

Comments URL: https://news.ycombinator.com/item?id=49727534

Points: 1

# Comments: 0

End AI agent lock-in. Start conversation with one agent – continue with another

yruzin — Wed, 02 Sep 2026 15:40:30 +0000

Article URL: https://github.com/Aplexica/Aplexica

Comments URL: https://news.ycombinator.com/item?id=49537958

Points: 1

# Comments: 0

Aplexica – keep memory and conversations when you leave Cursor for Claude

yruzin — Tue, 01 Sep 2026 16:44:47 +0000

Article URL: https://github.com/Aplexica/Aplexica

Comments URL: https://news.ycombinator.com/item?id=49524480

Points: 1

# Comments: 0

What 50 open source projects taught us about security in the AI era

yruzin — Sun, 16 Aug 2026 13:30:24 +0000

Article URL: https://github.blog/open-source/maintainers/what-50-open-source-projects-taught-us-about-security-in-the-ai-era/

Comments URL: https://news.ycombinator.com/item?id=49319889

Points: 4

# Comments: 1

Self-Evolving Coding Agents

yruzin — Wed, 12 Aug 2026 19:09:41 +0000

Article URL: https://arxiv.org/abs/2608.03392

Comments URL: https://news.ycombinator.com/item?id=49277180

Points: 2

# Comments: 0

Tailscale Mitigates the Lethal Trifecta

yruzin — Fri, 07 Aug 2026 12:05:55 +0000

Article URL: https://tailscale.com/blog/aperture-lethal-trifecta

Comments URL: https://news.ycombinator.com/item?id=49209141

Points: 3

# Comments: 0

A Hermes Agent Skill Looping Between Codex and Claude Code

yruzin — Sat, 01 Aug 2026 17:00:56 +0000

Article URL: https://codenote.net/en/posts/issue-to-pr-autonomous-loop-hermes-agent-skill/

Comments URL: https://news.ycombinator.com/item?id=49136162

Points: 1

# Comments: 0

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

yruzin — Sat, 01 Aug 2026 16:59:18 +0000

Article URL: https://arxiv.org/abs/2607.20759

Comments URL: https://news.ycombinator.com/item?id=49136144

Points: 2

# Comments: 0

The Kotlin Benchmark for AI Coding Agents

yruzin — Sat, 01 Aug 2026 16:58:42 +0000

Article URL: https://blog.jetbrains.com/kotlin/2026/07/introducing-the-kotlin-benchmark-evaluate-ai-coding-agents-on-real-world-kotlin-tasks/

Comments URL: https://news.ycombinator.com/item?id=49136137

Points: 2

# Comments: 0

New comment by yruzin in "Orca-Bench: How Ready Are Language Model Agents for Oncall?"

yruzin — Sat, 01 Aug 2026 16:56:31 +0000

I think this is where harness makes a lot of sense. Use LLM to produce all possible attack angles/phrases and just stupidly filter them out on input.

Orca-Bench: How Ready Are Language Model Agents for Oncall?

yruzin — Fri, 31 Jul 2026 18:32:43 +0000

Article URL: https://arxiv.org/abs/2607.28545

Comments URL: https://news.ycombinator.com/item?id=49126943

Points: 30

# Comments: 11

The GitHub Platform Era Is Over

yruzin — Wed, 29 Jul 2026 19:58:43 +0000

Article URL: https://julien.danjou.info/blog/the-github-platform-era-is-over/

Comments URL: https://news.ycombinator.com/item?id=49102245

Points: 3

# Comments: 0

The harness is all you need (mostly)

yruzin — Tue, 28 Jul 2026 23:05:54 +0000

Article URL: https://github.blog/ai-and-ml/github-copilot/the-harness-is-all-you-need-mostly/

Comments URL: https://news.ycombinator.com/item?id=49091209

Points: 2

# Comments: 0

No Snake Oil: Verifying Python Package Builds

yruzin — Mon, 27 Jul 2026 21:55:28 +0000

Article URL: https://arxiv.org/abs/2607.21888

Comments URL: https://news.ycombinator.com/item?id=49075982

Points: 3

# Comments: 0

No-Look Coding and the Five Stages of Grief

yruzin — Sun, 26 Jul 2026 13:21:25 +0000

Article URL: https://blog.kindel.com/2026/07/24/no-look-coding-and-the-five-stages-of-grief/

Comments URL: https://news.ycombinator.com/item?id=49057958

Points: 4

# Comments: 6

Just Say the Word

yruzin — Wed, 22 Jul 2026 21:27:59 +0000

Article URL: https://newsroom.spotify.com/2026-07-14/talk-to-spotify-announcement-beta/

Comments URL: https://news.ycombinator.com/item?id=49013702

Points: 3

# Comments: 0

Denying the Worm

yruzin — Wed, 22 Jul 2026 16:00:31 +0000

Article URL: https://www.crowdstrike.com/en-us/blog/denying-the-worm-sandworm-mode-and-ai-toolchain-supply-chain-attacks/

Comments URL: https://news.ycombinator.com/item?id=49008877

Points: 2

# Comments: 0

Malicious Agent Skills in the Wild

yruzin — Tue, 21 Jul 2026 02:55:20 +0000

Article URL: https://arxiv.org/abs/2602.06547

Comments URL: https://news.ycombinator.com/item?id=48987510

Points: 2

# Comments: 0

The /Goal Function Made Loop Engineering Click for Me

yruzin — Mon, 20 Jul 2026 19:40:00 +0000

Article URL: https://bhart.org/articles/the-goal-function-made-loop-engineering-click-for-me

Hacker News: yruzin

Show HN: Aplexica – resume a Claude Code conversation in Codex, and back

End AI agent lock-in. Start conversation with one agent – continue with another

Aplexica – keep memory and conversations when you leave Cursor for Claude

What 50 open source projects taught us about security in the AI era

Self-Evolving Coding Agents

Tailscale Mitigates the Lethal Trifecta

A Hermes Agent Skill Looping Between Codex and Claude Code

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

The Kotlin Benchmark for AI Coding Agents

New comment by yruzin in "Orca-Bench: How Ready Are Language Model Agents for Oncall?"

Orca-Bench: How Ready Are Language Model Agents for Oncall?

The GitHub Platform Era Is Over

The harness is all you need (mostly)

No Snake Oil: Verifying Python Package Builds

No-Look Coding and the Five Stages of Grief

Just Say the Word

Denying the Worm

Malicious Agent Skills in the Wild

The /Goal Function Made Loop Engineering Click for Me

A Scorecard for the AI Age