Hacker News

Ask HN: OpenAI models vs. Gemini 2.5 Pro for coding and swe

Hacker News - Wed, 04/23/2025 - 11:35am

In your experience, which of the two models (all of OpenAI vs Gemini 2.5 Pro) are better for having as assistants to ask SWE/software systems related questions and doing long and complex reasoning?

I'm debating whether there's any point in paying for ChatGPT vs. paying (or even using the free version) of Gemini 2.5 Pro.

I have the feeling that most HNers prefer the latter, however in livebench I think OpenAI surpasses Gemini for coding.

Comments URL: https://news.ycombinator.com/item?id=43773345

Points: 1

# Comments: 1

Categories: Hacker News

Vibing Code Quality

Hacker News - Wed, 04/23/2025 - 11:32am
Categories: Hacker News

Suna AI General AI Agent

Hacker News - Wed, 04/23/2025 - 11:31am

Article URL: https://sunaai.ai/

Comments URL: https://news.ycombinator.com/item?id=43773309

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: MazeRace – a simple multiplayer maze game

Hacker News - Wed, 04/23/2025 - 11:30am

I made a simple multiplayer game called MazeRace.

You can either create a private room or join someone else’s room using a code. The server generates a new maze for each room, and players race from the start to the end point. You also see other players moving in real time

It’s not super fancy, but it's playable and kinda fun.

Would love feedback or ideas!

Comments URL: https://news.ycombinator.com/item?id=43773295

Points: 1

# Comments: 0

Categories: Hacker News

How AI Agents work and how to build them

Hacker News - Wed, 04/23/2025 - 11:24am

Article URL: https://slobodan.me/posts/ai-agents/

Comments URL: https://news.ycombinator.com/item?id=43773237

Points: 1

# Comments: 0

Categories: Hacker News

Ask HN: What's missing in AI prompt validation and security tools?

Hacker News - Wed, 04/23/2025 - 10:43am

We've been building a middleware layer that acts like a firewall for LLMs, it sits between the user and the model (OpenAI, Claude, Gemini, etc.) and intercepts prompts and responses in real time.

It blocks prompt injection, flags hallucinations, masks PII, and adds logging + metadata tagging for compliance and audit.

But we’re hitting the classic startup blind spot: we don’t want to build in a vacuum.

What do you feel is still broken or missing when it comes to: - Securing LLM prompts/responses? - Making GenAI safe for enterprise use? - Auditing what the AI actually said or saw?

We’d love your feedback — especially if you’re working on or thinking about GenAI in production settings.

Thanks!

Comments URL: https://news.ycombinator.com/item?id=43772798

Points: 1

# Comments: 0

Categories: Hacker News

Pages