Hackernews posts about Gemini Flash

1. When Reasoning Becomes a Trap: Gemini 3 Flash in FoodTruck Bench (foodtruckbench.com)
   4 points by Munksgaard 17 days ago | discuss
2. I accidentally managed to uncover the system prompt of Google Gemini 3 Flash (pastebin.com)
   4 points by errorcodezero 29 days ago | discuss
3. Gemini-flash-latest silently broke Search grounding for 1 month
   2 points by takibboinz 15 days ago | discuss
4. When Reasoning Becomes a Trap: Gemini 3 Flash in FoodTruck Bench (foodtruckbench.com)
   2 points by YeGoblynQueenne 17 days ago | discuss
5. Show HN: Claude Code skills that build complete Godot games (github.com)
   337 points by htdt 5 days ago | 205 comments
6. Show HN: Optimize_anything: A Universal API for Optimizing Any Text Parameter (gepa-ai.github.io)
   8 points by LakshyAAAgrawal 29 days ago | discuss
7. Show HN: Dwarf.land – autonomous dwarf civilization SIM with AI model routing (dwarf.land)
   4 points by kulesh 5 days ago | 4 comments
8. CostRouter – Cut AI API costs 60% by routing to the cheapest capable model
   4 points by alex_1002 9 days ago | discuss
9. Show HN: Omni-Glass – Rust app that turns screen pixels into MCP tool calls (github.com)
   3 points by goshtasb 28 days ago | 1 comments
10. How long till every major provider sets their RSI loops in motion?
    3 points by foxindustrial 9 days ago | discuss
11. Show HN: Tri·TFM Lens – 5-axis quality evaluation for ChatGPT/Gemini responses
    2 points by siris950 15 days ago | 1 comments
12. Show HN: OmniGlass – Executable AI screen snips with kernel-level sandboxing (github.com)
    2 points by goshtasb 19 days ago | discuss
13. Show HN: Private AI assistant for $1.99 -Free AI (personalassistantdeploy.com)
    2 points by robotaxi 24 days ago | discuss
14. Show HN: InferShrink – Cut LLM API costs 10x with automatic model routing (pypi.org)
    2 points by doronp 24 days ago | discuss
15. Show HN: Quill – A system-wide tech dictionary for the AI coding era (github.com)
    2 points by c3nx 28 days ago | discuss
16. Show HN: Extract (financial) data from emails with local LLM (github.com)
    1 points by brainless 11 days ago | 1 comments
17. Show HN: HN Jobs Trends – Monthly trend analysis of HN job postings (hn-job-trends.gantryops.dev)
    1 points by notdian 6 days ago | discuss
18. Show HN: AI Benchy – AI benchmarks and comparisons (aibenchy.com)
    1 points by XCSme 15 days ago | discuss
19. A proxy that cuts LLM API bills by routing simple tasks to cheaper models
    1 points by alex_1002 18 days ago | discuss
20. Show HN: I built an expense tracker where no data ever touches a server (github.com)
    1 points by ankitpandey2708 18 days ago | discuss
21. Show HN: AdaptGauge – I found that adding few-shot examples can make LLMs worse (github.com)
    1 points by shuntaro-okuma 21 days ago | discuss
22. Show HN: Right-click any text on macOS to add it to your calendar (open-source) (github.com)
    1 points by mollynpaan 23 days ago | discuss
23. Show HN: Prompt2pwn – CTF Automated Solver (github.com)
    1 points by bigEnotation 25 days ago | discuss
24. Show HN: LLMWise – Compare, Blend, and Judge LLM Outputs from One API (llmwise.ai)
    1 points by dm118 29 days ago | discuss
25. Nano Banana 2 (deepmind.google)
    8 points by meetpateltech 23 days ago | 2 comments
26. Show HN: Reverse-engineer any site's API from inside the browser (www.rtrvr.ai)
    5 points by arjunchint about 13 hours ago | 1 comments
27. Grok 4.20 brings minimal improvements over Grok-4.1-fast (aibenchy.com)
    2 points by XCSme 9 days ago | 1 comments
28. Ask HN: Are MiniMax Models Scams?
    3 points by XCSme 3 days ago | 1 comments
29. Show HN: I built an AI senior architect – vibe coding meets system design (www.sysdesai.com)
    2 points by BetterForAll 24 days ago | 2 comments
30. Show HN: Nano Banana 2 – Sub-second AI image gen via Gemini 3.1 Flash (nano-banana2.me)
    1 points by naxtsass 22 days ago | discuss