Hacker News: onurkanbkrc

Build, deploy, and scale agents at any level (L1–L5)

onurkanbkrc — Wed, 08 Jul 2026 13:35:39 +0000

Article URL: https://github.com/scaleapi/scale-agentex

Comments URL: https://news.ycombinator.com/item?id=48831782

Points: 2

# Comments: 0

Awesome Codex Automations

onurkanbkrc — Sun, 26 Apr 2026 16:55:39 +0000

Article URL: https://github.com/onurkanbakirci/awesome-codex-automations

Comments URL: https://news.ycombinator.com/item?id=47911760

Points: 1

# Comments: 0

Show HN: AgentLint – ESLint for your coding agents

onurkanbkrc — Tue, 07 Apr 2026 13:05:10 +0000

I’ve been spending a lot of time with coding agents lately. Across Claude Code, Cursor, OpenCode, Codex, and different models, I kept noticing that some people were getting much better results from the same tools. It became clear that this was not just about prompting.

A big part of it was context drift. AGENTS.md, skills, rules, and workflows looked fine, but were no longer aligned with the code.

I also learned that more context does not always help. Sometimes it adds noise and wastes tokens. The recent AGENTS.md paper also pushed me to think harder about this, especially around auto-generated context files and /init-style workflows.

Then I saw Microsoft’s writeup showing a jump from 38.1% to 69% after improving instruction setup. That made me take these files much more seriously.

AgentLint came out of that. It’s a small CLI that scans the repo and helps keep context files aligned. After setup, MCP handles most of the ongoing flow.

Give it a try: npx @agent-lint/cli

http://samilozturk.github.io/agentlint

Would really appreciate any feedback or criticism.

Comments URL: https://news.ycombinator.com/item?id=47674729

Points: 4

# Comments: 3

The Anatomy of an Agent Harness

onurkanbkrc — Tue, 07 Apr 2026 09:14:48 +0000

Article URL: https://blog.langchain.com/the-anatomy-of-an-agent-harness/

Comments URL: https://news.ycombinator.com/item?id=47672551

Points: 1

# Comments: 0

Show HN: SFT to convert a base language model into a conversational chat model

onurkanbkrc — Wed, 04 Mar 2026 09:23:49 +0000

Article URL: https://github.com/onurkanbakirci/Llama-2-7b-oasst-sft

Comments URL: https://news.ycombinator.com/item?id=47245056

Points: 1

# Comments: 0

Show HN: Minisft – from base model to chat model

onurkanbkrc — Sun, 15 Feb 2026 10:03:31 +0000

Article URL: https://github.com/onurkanbakirci/Llama-2-7b-oasst-sft

Comments URL: https://news.ycombinator.com/item?id=47022508

Points: 1

# Comments: 0

New comment by onurkanbkrc in "ai;dr"

onurkanbkrc — Fri, 13 Feb 2026 09:16:03 +0000

LLMs are trained on vast portions of the internet.

In that sense, they are essentially systems that mimic online content.

Therefore, what an AI generates often reflects the perspectives of the people who originally created the training data, rather than the true thoughts of the person prompting it.