Hackernews posts about GPT-4 LLM
- Small LLMs can outperform GPT-4 at detecting jailbreaks (romaingrx.com)
- Configuring GH Codespaces with UV/node + llm tool + free GPT4.1 w/$GITHUB_TOKEN (til.simonwillison.net)
- Show HN: LLM Opinion – discover what sources an LLM relies on (llm-opinion.onrender.com)
- Show HN: I spent 40 hours vibe coding after 40 years of traditional programming (marcobenedetti.substack.com)
- Show HN: I made an interactive prompt compression demo (www.promptropy.com)
- Show HN: Cinematic Rolplay with Wan 2.2 (www.reveriedr.com)
- GPT-4 LLM simulates people well enough to replicate social science experiments (www.treatmenteffect.app)
- Chinese researchers build military AI using Meta's open-source Llama model (www.tomshardware.com)
- Ask HN: Compiling GPT-4 model card (klu.ai)
- Using AI to Automatically Jailbreak GPT-4 and Other LLMs in Under a Minute (www.robustintelligence.com)
- Llama 2, CodeLlama, and GPT-4 performance: recent LLM developments and research (magazine.sebastianraschka.com)
- LLM-Ready Training Dataset for Apple's Foundation Models (iOS 26) (rileyhealth.gumroad.com)
- Show HN: Technical diagrams were slowing me down, so I built a faster way (www.rapidcharts.ai)
- Show HN: Story Generator (github.com)
- Show HN: SquadGPT – chat interface to LLMs for teams (squadgpt.ai)
- Show HN: Code+=AI – build AI webapps in minutes by having LLM complete tickets (codeplusequalsai.com)
- Show HN: Interactive price comparison for AI models (LLMs and Speech-to-Text) (ai-pricing.vercel.app)
- Show HN: My related-posts finder script (with LLM and GPT4 enhancement) (tomhazledine.com)
- Evaluating 55 LLMs with GPT-4 (benchmarks.llmonitor.com)
- First open source model LLM beats GPT-4-0613 and GPT-4-0314 (huggingface.co)
- Apple's 3B LLM Outperforms GPT-4 (unwindai.substack.com)
- Beating GPT-4 with Open Source LLMs (www.latent.space)
- Junior LLM – Automate GPT-4 Multi-File Edits with Coding Agent (marketplace.visualstudio.com)