Top New Best Ask Show Jobs

yruzin

36 karma · joined July 9, 2026

submissions comments

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

github.com·1 pts·yruzin·

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

github.com·1 pts·yruzin·

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

github.com·1 pts·yruzin·

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

github.blog·4 pts·yruzin·

Self-Evolving Coding Agents

arxiv.org·2 pts·yruzin·

Tailscale Mitigates the Lethal Trifecta

tailscale.com·3 pts·yruzin·

A Hermes Agent Skill Looping Between Codex and Claude Code

codenote.net·1 pts·yruzin·

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

arxiv.org·2 pts·yruzin·

The Kotlin Benchmark for AI Coding Agents

blog.jetbrains.com·2 pts·yruzin·

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

arxiv.org·30 pts·yruzin·

The GitHub Platform Era Is Over

julien.danjou.info·3 pts·yruzin·

The harness is all you need (mostly)

github.blog·2 pts·yruzin·

No Snake Oil: Verifying Python Package Builds

arxiv.org·3 pts·yruzin·

No-Look Coding and the Five Stages of Grief

blog.kindel.com·4 pts·yruzin·

Just Say the Word

newsroom.spotify.com·3 pts·yruzin·

Denying the Worm

crowdstrike.com·2 pts·yruzin·

Malicious Agent Skills in the Wild

arxiv.org·2 pts·yruzin·

The /Goal Function Made Loop Engineering Click for Me

bhart.org·3 pts·yruzin·

A Scorecard for the AI Age

openai.com·3 pts·yruzin·

Prompts and Skills need a system of record

mistral.ai·2 pts·yruzin·

The Server Is a Sync Relay Now: Architecting Around Client-Owned State

tiarebalbi.com·3 pts·yruzin·

Building scalable AI agents with modular prompt transpilation

developers.googleblog.com·8 pts·yruzin·