English

Posts with #AI4code

#AI4code

Public posts on X that use #AI4code.

Related hashtags

  1. Alexey Svyatkovskiy@asvyatko
    The Data & AI team at Microsoft seeks a Principal Research Scientist to contribute to the next generation of AI-assisted developer tools 🚀 💡 Copilot model improvements 💡 Copilot AI for pull requests (code review, program repair, ...) Message me if interested #ai4code #copilots
    107443
  3. Awesome Papers@awesomepapersio
    💻 AI for Code · paper of the day GLM-5: from Vibe Coding to Agentic Engineering The number that matters: Through these innovations, GLM-5… GLM-5-Team: Aohan Zeng et al. · 2026 ⭐ 6,936 GitHub stars 🔗 #AI4Code #CodeGen #SoftwareEngineering
    Download
    0002
  4. Yasharth Bajpai✓@imYbajpai
    After 36 hours of travel, finally at Porto de Galinhas, Brazil to attend @AIwareConf @FSEconf . I'll be here throughout the conference and would love to discuss #AI4Code & #AI4SE in general. Also, share our learnings from building GitHub Copilot inside VS. DMs are open.
    Download
    35262K
  5. Michele Catasta✓@pirroh
    Talking about AI4Code and eating Italian food 🍝 Couldn’t ask for a better time in Milano. Thanks for the invite, @bendingspoons 🙏 And kudos for organizing an unprecedented #AI event in Italy:
    Bending Spoons @bendingspoons
    Michele Catasta, @pirroh, head of applied research at @Theteamatx, presents at #Synapse #AISymposium on #AI and #LLMs in source code: “We barely scratched the surface of which tasks can be tackled by large language models. “
    127
  7. Michele Catasta✓@pirroh
    @pirroh
    And here is the video of my talk: if you’d like to spend ~1hr hearing my high-level takes on Large Language Models, PaLM-Coder and #AI4Code in general. 👉 I’m hiring a talented ML Research Engineer in NLP / LLMs. Reach out to me if that’s your passion!
    004
  8. Baishakhi Ray@baishakhir
    Updating real-world large legacy projects like binutils? Meet ( C2SaferRust: leveraging program analysis & LLMs to create idiomatic, safer Rust with (↓38%) raw pointers & (↓28%) unsafe code while preserving functionality 🚀 #rustlang #AI4code #AIAgent
    12372.3K
  9. Kaggle@kaggle
    Check our our new #ai4code competition with @google and @theteamatx! Understand the relationship between code and comments in Python notebooks:
    010103
  11. Michele Catasta✓@pirroh
    "Small" Language Models are the sweet spot that will bring #AI4Code to every developer in the world. Low latency is paramount when it comes to UX! @amasad, @samipddd and the whole @Replit team accomplished the unthinkable today. I couldn't be more proud.
    Amjad Masad @amasad
    In 2018 we announced Multiplayer Mode. Since then, Replit became the world's leading collaborative editor. Today, we're announcing AI Mode, which infuses state-of-the-art intelligence into nearly all IDE features, the next major evolution for Replit:
    2327
  12. Amjad Masad✓@amasad
    In 2018 we announced Multiplayer Mode. Since then, Replit became the world's leading collaborative editor. Today, we're announcing AI Mode, which infuses state-of-the-art intelligence into nearly all IDE features, the next major evolution for Replit:
    Download
    553842.8K
  13. Tao Yu@taoyds
    #NLProc #AI4Code GPT-3 Codex is possible to generate INTERACTIVE multi-vis interfaces📈 (not just static simple plots!) from natural language queries! Check out our demo below! Work led by @Yiru__Chen @sirrice. Stay tuned for fancier ones!
    Yiru Chen @Yiru__Chen
    No programming, No learning curve! We can now generate INTERACTIVE multi-vis interfaces from NL queries! Yes! Directly from NL! Check this demo below. I will also give a talk on this next Sat in the NLVIS workshop @IEEEVIS. Paper:
    007
  14. Yiru Chen@Yiru__Chen
    No programming, No learning curve! We can now generate INTERACTIVE multi-vis interfaces from NL queries! Yes! Directly from NL! Check this demo below. I will also give a talk on this next Sat in the NLVIS workshop @IEEEVIS. Paper:
    Download
    1240
  15. Baishakhi Ray@baishakhir
    Introducing SemCoder, a semantic-aware Code LLM excelling in code generation and execution reasoning. Trained with high-quality data and novel way of aligning execution, only 6.7B model is outperforming GPT3.5 and CodeLlama 34B. link: #LLMs, #AI4Code
    110828.9K
  16. Tao Yu@taoyds
    A new way to work w. LMs! Binder, an easy neuro-symbolic paradigm: 1.Parse input➡️SQL/Python bound w. GPT3 Codex API calls 2.Codex+PL interpreter execute➡️answer No train&few-shot!➡️SOTA 🆚chain-of-thought: interpretable&robust⬆️ 🆚NL2Code: coverage⬆️
    Download
    1073286
  17. Tao Yu@taoyds
    @taoyds
    🆚End2end/chain-of-thought: Binder program’s deterministic execution entails prediction/answer➡️interpretable & robust⬆️ 🆚#SemPar #AI4Code: Binder injects Codex functionalities in SQL/Python to handle more diverse questions➡️coverage⬆️ Demo: 2/8
    109
  18. Pushmeet Kohli✓@pushmeet
    Following up on the AlphaEvolve code opt. agent, I am happy to share how our team at @GoogleDeepMind has developed the CodeMender agent to design/apply patches to fix security vulnerabilities in large scale open source projects. #AI4code Read more at:
    42521013.8K
  20. Rajaswa Patil✓@RajaswaPatil
    🚨 New Paper Alert 🚨 Our paper - "Program Synthesis for Complex QA on Charts via Probabilistic Grammar Based Filtered Iterative Back-Translation" - has been accepted at the @eaclmeeting 2023 conference as a Findings paper! 🥳🎉 @TCSResearch #AI4Code #NSAI #NLProc
    41473.3K
  23. Theo X. Olausson@theo_olausson
    By popular request, the submission deadline for the #VerifAI workshop at @iclr_conf has been extend to Sunday, Feb 8 (AoE) 🎉🎉 🎉 But don't leave it until the last minute - submit your papers on RLVR, AI+verification, #ai4code and #ai4math now! 👉
    Download
    0151.2K
  25. Theo X. Olausson@theo_olausson
    #ai4code peeps at #ICLR2024: come chat self-repair with me at 10:45 AM on Friday, May 10! I'll be presenting the camera-ready version of this fan favorite from last year... now with even more data! Keep reading for a sneak peek of the results 👇
    Download
    AK @_akhaliq
    Demystifying GPT Self-Repair for Code Generation paper page: Large Language Models (LLMs) have shown remarkable aptitude in code generation but still struggle on challenging programming tasks. Self-repair -- in which the model debugs and fixes mistakes in its own code -- has recently become a popular way to boost performance in these settings. However, only very limited studies on how and when self-repair works effectively exist in the literature, and one might wonder to what extent a model is really capable of providing accurate feedback on why the code is wrong when that code was generated by the same model. In this paper, we analyze GPT-3.5 and GPT-4's ability to perform self-repair on APPS, a challenging dataset consisting of diverse coding challenges. To do so, we first establish a new evaluation strategy dubbed pass@t that measures the pass rate of the tasks against the total number of tokens sampled from the model, enabling a fair comparison to purely sampling-based approaches. With this evaluation strategy, we find that the effectiveness of self-repair is only seen in GPT-4. We also observe that self-repair is bottlenecked by the feedback stage; using GPT-4 to give feedback on the programs generated by GPT-3.5 and using expert human programmers to give feedback on the programs generated by GPT-4, we unlock significant performance gains.
    25247K
  26. AK✓@_akhaliq
    Demystifying GPT Self-Repair for Code Generation paper page: Large Language Models (LLMs) have shown remarkable aptitude in code generation but still struggle on challenging programming tasks. Self-repair -- in which the model debugs and fixes mistakes in its own code -- has recently become a popular way to boost performance in these settings. However, only very limited studies on how and when self-repair works effectively exist in the literature, and one might wonder to what extent a model is really capable of providing accurate feedback on why the code is wrong when that code was generated by the same model. In this paper, we analyze GPT-3.5 and GPT-4's ability to perform self-repair on APPS, a challenging dataset consisting of diverse coding challenges. To do so, we first establish a new evaluation strategy dubbed pass@t that measures the pass rate of the tasks against the total number of tokens sampled from the model, enabling a fair comparison to purely sampling-based approaches. With this evaluation strategy, we find that the effectiveness of self-repair is only seen in GPT-4. We also observe that self-repair is bottlenecked by the feedback stage; using GPT-4 to give feedback on the programs generated by GPT-3.5 and using expert human programmers to give feedback on the programs generated by GPT-4, we unlock significant performance gains.
    Download
    5122491413K
  27. Show more posts