English

Posts with #CodeGeneration

#CodeGeneration

Public posts on X that use #CodeGeneration.

Related hashtags

  1. Topvon Ai@TopvonA
    🚨 Topvon AI Update – 10 Days Away! 🚀 Get ready for GPT-5.2 for auto code generation & fixing, and Gemini 3 for code editing & asset creation. Join our community & be the first to test it: 👉 #AI #GameDev #CodeGeneration #TopvonAI
    04595
  3. Jace@Jace_blog
    A proposed protocol to test whether symbolic prompts beat plain language in LLM code generation. Seven conditions, hidden tests, token costs. No results claimed. Open harnesses included. #LLM #PromptEngineering #CodeGeneration #SymbolicPersonaCoding #AI
    Jace @Jace_blog
    Web-grounded AI depends on online evidence that can vanish or change. This paper examines link rot, content drift, and source spoofing, outlining ways to assess source integrity without assuming interference. #WebGroundedAI #ContentDrift #DataPoisoning
    1111437
  4. Jace@Jace_blog
    Web-grounded AI depends on online evidence that can vanish or change. This paper examines link rot, content drift, and source spoofing, outlining ways to assess source integrity without assuming interference. #WebGroundedAI #ContentDrift #DataPoisoning
    018322
  9. Victoria X Lin✓@VictoriaLinML
    💫 New work by @AnsongNi from his internship @MetaAI. LEVER is a simple approach that improves code generation from LLMs by learning to verify the generated program (✅ or ❌) given the NL goal + context description, the program itself and its execution outcome. #codegeneration
    Ansong Ni @AnsongNi
    Execution results are strong indicators of program correctness. But how can we improve LLMs for code generation with execution? In our new paper, we propose LEVER, a simple method that learns to verify and rerank LLM-generated programs with their execution results. 🧵👇 (1/n)
    05388.2K
  10. Ansong Ni✓@AnsongNi
    Execution results are strong indicators of program correctness. But how can we improve LLMs for code generation with execution? In our new paper, we propose LEVER, a simple method that learns to verify and rerank LLM-generated programs with their execution results. 🧵👇 (1/n)
    Download
    339242131K
  11. Extrapolator AI✓@extrapolatorai
    📰 PSI Research publishes five AI-proved quantum information theorems PSI Research used its AI system to resolve five open quantum information problems, each delivered with a paper, Lean... Read more → #AI #AITools #CodeGeneration #AIReasoning
    Download
    00132
  13. Extrapolator AI✓@extrapolatorai
    📰 MiRL Targets Recurring Terminal Agent Errors for RL Training MiRL finds recurring terminal agent errors and retrains via RL at those steps, cutting misbehaviors 43 to 57 percent with 35 percent... Read more → #AI #AIAgents #CodeGeneration #FineTuning
    Download
    0009
  14. Extrapolator AI✓@extrapolatorai
    📰 CodeRabbit deploys GPT-6.1 Sol for cross-file security audit CodeRabbit deploys GPT-6.1 Sol in a dual-agent pipeline to detect security vulnerabilities and propose developer-ready patches... Read more → #AIAgents #AIIndustry #CodeGeneration #LLM
    Download
    00019
  23. Show more posts