Hackernews posts about GPT-4 LLM

1. Scaling tool orchestration data will emerge different intelligence and LLMs
   2 points by arkariarn 4 days ago | discuss
2. I'm 11 and trained a custom MoE LLM for $1
   4 points by Hey1-Arthur 16 days ago | discuss
3. Show HN: A 3-line wrapper that enforces deterministic security for AI agents
   1 points by tonyww 25 days ago | discuss
4. Show HN: VectorLens – See why your RAG hallucinates, no config
   1 points by gustav-proxi 29 days ago | discuss
5. GPT-4 LLM simulates people well enough to replicate social science experiments (www.treatmenteffect.app)
   223 points by thoughtpeddler over 1 year ago | 94 comments
6. Ask HN: How are LLMs getting smarter beyond just scaling?
   2 points by chenxi9649 over 1 year ago | discuss
7. Chinese researchers build military AI using Meta's open-source Llama model (www.tomshardware.com)
   5 points by AnhTho_FR over 1 year ago | discuss
8. I spent a year and $5,700 to see if ChatGPT can beat the market (S&P 500)
   39 points by ishtiaqrahman almost 2 years ago | 42 comments
9. LLM-Ready Training Dataset for Apple's Foundation Models (iOS 26) (rileyhealth.gumroad.com)
   13 points by rileygersh 9 months ago | 5 comments
10. Show HN: Technical diagrams were slowing me down, so I built a faster way (www.rapidcharts.ai)
    5 points by SamiCostox 9 months ago | discuss
11. I created a new training dataset for stale SOTA LLMs
    2 points by rileygersh 9 months ago | discuss
12. Show HN: Docs-to-Markdown – Convert Documentation URLs into Markdown (github.com)
    2 points by frandagostino about 1 year ago | discuss
13. Ask HN: Has anyone seen this before in any ChatGPT?
    1 points by HereticGlaux 10 months ago | 1 comments
14. Ask HN: Algorithm for searching text with similar meaning
    1 points by delduca almost 2 years ago | 1 comments
15. Show HN: Open-sourced AI Agent runtime (YAML-first) (github.com)
    1 points by nsokra02 about 1 month ago | discuss
16. Show HN: Code+=AI – build AI webapps in minutes by having LLM complete tickets (codeplusequalsai.com)
    1 points by cryptoz 12 months ago | discuss
17. Show HN: Interactive price comparison for AI models (LLMs and Speech-to-Text) (ai-pricing.vercel.app)
    1 points by nuxdie over 1 year ago | discuss
18. First open source model LLM beats GPT-4-0613 and GPT-4-0314 (huggingface.co)
    5 points by spxneo almost 2 years ago | discuss
19. ShellGPT: A CLI productivity tool powered by LLMs like GPT-4 (github.com)
    3 points by sea-gold over 1 year ago | 1 comments
20. I built a simple comparison tool for LLMs (like GPT-4, Claude, Gemini) (thesota.fyi)
    2 points by edonadei over 1 year ago | 1 comments
21. Show HN: KoppieOS,smart launcher,Chat both gpt4 and safe local LLM with avatar (koppieos.koppie.ai)
    1 points by jammieRuo almost 2 years ago | discuss
22. Ask HN: Why is ChatGPT so bad at electronics?
    22 points by pera over 1 year ago | 44 comments
23. Show HN: Open-source study to measure end user satisfaction levels with LLMs (open-llm-initiative.com)
    12 points by sparacha over 1 year ago | 2 comments
24. Show HN: I open-sourced a $1M engine for closing loops in embedding space (github.com)
    8 points by WFGY 9 months ago | 10 comments
25. Show HN: PromptL, a templating language designed for LLM prompting (promptl.ai)
    7 points by heycesr over 1 year ago | 4 comments
26. Show HN: Towards agentic Graph RAG: Enhancing graph retrieval with vector search (blog.kuzudb.com)
    6 points by laminarflow027 10 months ago | discuss
27. Show HN: Lailaims – Talk to multiple LLMs at once (lailaims.pages.dev)
    6 points by youz 11 months ago | discuss
28. Show HN: I built a tool to make system design diagrams less painful (www.rapidcharts.ai)
    4 points by SamiCostox 9 months ago | discuss
29. Would you use an LLM that follows instructions reliably?
    3 points by gdevaraj 10 months ago | 5 comments
30. Show HN: LLM In-Browser Fuzzer Finds Hidden Prompt Injection in AI Browsers (browsertotal.com)
    3 points by minche 6 months ago | discuss
31. Show HN: Directed Intelligence – Smarter, More Reliable LLMs (directedintelligence.org)
    3 points by camwest over 1 year ago | discuss
32. Access LLM from Within Gsheet
    2 points by aidopper 10 months ago | 2 comments
33. Show HN: I made an AI content guessing game (usetopical.com)
    2 points by TheIndieBuilder over 1 year ago | discuss
34. Ask HN: What if the AI scaling plateau is just a "false dip"?
    1 points by massicerro 3 months ago | 3 comments