Hackernews posts about Gemini LLM

1. Updated LLM Benchmark (Gemini 3 Flash) (entropicthoughts.com)
   3 points by ibobev 2 days ago | discuss
2. How to scale after first paying customer?
   2 points by machopanko 23 days ago | 1 comments
3. AI Playground - free comparison and test lab for LLMs(GPT, Claude, Gemini, more)
   1 points by mohiuddinansari 15 days ago | 1 comments
4. Show HN: Browser-Use as a REST API with VNC, persistent sessions, and tools (github.com)
   2 points by Reqeique 19 days ago | discuss
5. Show HN: LLMSwap – Switch between LLM providers with one line of code (github.com)
   3 points by sreenathmenon 6 days ago | 1 comments
6. Show HN: CRD Wizard – A GUI for Kubernetes Custom Resource Definitions (github.com)
   2 points by pehli 8 days ago | discuss
7. Show HN: I built the fastest AI app builder that I can find (vibes.higashi.blog)
   1 points by yuedongze 8 days ago | 4 comments
8. Show HN: The Journal of AI Slop – an AI peer-review journal for AI "research" (www.journalofaislop.com)
   5 points by popidge 29 days ago | discuss
9. Ask HN: Why I can't enable Chrome Gemini Nano on my MacBook with M1?
   1 points by denis4inet 5 days ago | discuss
10. Show HN: Chorus – Multi-agent debate through epistemological framework collision (chorusai.replit.app)
    1 points by efoobz 25 days ago | discuss
11. Show HN: HN Wrapped 2025 - an LLM reviews your year on HN (hn-wrapped.kadoa.com)
    313 points by hubraumhugo 12 days ago | 153 comments
12. Ask HN: How are you LLM-coding in an established code base?
    70 points by adam_gyroscope 16 days ago | 66 comments
13. Show HN: Solving the ~95% legislative coverage gap using LLM's (lustra.news)
    41 points by fokdelafons 16 days ago | 23 comments
14. LLM Benchmark: Frontier models now statistically indistinguishable
    7 points by js4ever 12 days ago | 4 comments
15. Show HN: Forecaster Arena – Testing LLMs on real events with prediction markets (forecasterarena.com)
    4 points by setrf 21 days ago | discuss
16. Show HN: Agentica – 200 reqs/day for free, data not used to train our LLMs (agentica.genlabs.dev)
    3 points by GenLabs-AI 9 days ago | discuss
17. Show HN: Chrome extension for searching past conversations across LLMs (conversai.us)
    3 points by ljubomir 27 days ago | discuss
18. Show HN: Gemini has a "Concrete Bias" against minimalist software (Basecamp vs (www.genrankengine.com)
    2 points by arunkumars91 3 days ago | 2 comments
19. Show HN: Drawing Guessing Game with an LLM (llmparty.pixeletes.com)
    2 points by victornomad 17 days ago | 1 comments
20. I made a prompt framework that makes LLMs stop hedging and speak straight
    2 points by DrRockzos 25 days ago | 1 comments
21. Project Bhavanga: Fixing LLM Context Dilution with Buddhist Psychology
    2 points by DosankoTousan 26 days ago | 1 comments
22. Show HN: A Multi-agent system where LLMs challenge each other's answers
    2 points by AlphaSean 2 days ago | discuss
23. Show HN: LLMKit – Compare LLMs side-by-side with real-time streaming (www.llmkit.cc)
    2 points by chieund 10 days ago | discuss
24. Show HN: A lightweight DLP browser extension to prevent data leaks in LLM tools (www.asturic.com)
    2 points by __alberto 14 days ago | discuss
25. Would you pay for a tool that executes LLM code to verify it?
    2 points by ZOdex 16 days ago | discuss
26. Show HN: ZON-TS 50–65% fewer LLM tokens zero parse overhead better than TOON/CSV (zonformat.org)
    2 points by ronibhakta 23 days ago | discuss
27. Show HN: Testing how symbolic framing affects LLMs
    1 points by Daladim about 4 hours ago | 1 comments
28. Ask HN: Are LLMs becoming a real discovery channel for ecommerce?
    1 points by David_0101 5 days ago | 1 comments
29. Show HN: Gemini, OpenAI, Claude, Grok and Mistral argue over everything (llmxllm.com)
    1 points by mananonhn 18 days ago | 1 comments
30. Show HN: OpenAPI-batch: library for batch execution of LLM requests (github.com)
    1 points by spannercode 5 days ago | discuss