Show HN: Pilot your motorcycle across increasingly wild roller coaster geometry https://ift.tt/61B8I7b

Show HN: Pilot your motorcycle across increasingly wild roller coaster geometry I began this project in the 2010s to teach myself Unity and C#. Each piece of 3D geometry was made inside of the Unity IDE with the free ProBuilder suite of simple modeling tools. Should work in the browser on both phones and personal computers! https://ift.tt/aMrs9x3 August 26, 2023 at 05:47PM

Show HN: Our latest AI creation, all feedback and discussions welcome https://ift.tt/GwsXzg6

Show HN: Our latest AI creation, all feedback and discussions welcome Please Check out our Latest AI content generation Tool LogicBalls AI. Please give your feedback and suggestions. https://logicballs.com August 26, 2023 at 02:47PM

Show HN: Email Enricher, a Free, Offline Clearbit Alternative https://ift.tt/R6SjWbz

Show HN: Email Enricher, a Free, Offline Clearbit Alternative At my prior employer, we got Slack alerts for big company sign-ups I wanted the same for my new startup ( https://fillout.com ) but quickly found that Clearbit would cost us $7,000 / mo... Instead, I made this free npm package `email-enricher` the returns if an email is likely from a Fortune 1000 company Hope it's useful to someone else! https://ift.tt/BYwP2SR August 26, 2023 at 02:51AM

Show HN: Display primary keys the way humans and developers prefer https://ift.tt/5ITpe0A

Show HN: Display primary keys the way humans and developers prefer https://ift.tt/RsAYJ86 August 26, 2023 at 03:20PM

Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas https://ift.tt/CAMzgnI

Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas AhaApple. AI Idea Generator. One click, Many Creative and Novel Ideas. Leveraging AI, many brainstorming techniques, and many innovative techniques, AhaApple make it easy for you to gain more inspirations and ideas. https://ift.tt/URtpoTm August 26, 2023 at 10:22AM

Show HN: Full list of ChatGPT Plugins and stats https://ift.tt/hwGAq4z

Show HN: Full list of ChatGPT Plugins and stats https://ift.tt/USv92kK August 25, 2023 at 09:12PM

Show HN: Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B https://ift.tt/2bm4nYs

Show HN: Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B Hi HN, We have fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset that achieved 67.6% and 69.5% pass@1 on HumanEval, respectively. GPT-4 achieved 67%. To ensure result validity, we applied OpenAI's decontamination methodology to our dataset. The CodeLlama models released yesterday demonstrate impressive performance on HumanEval. - CodeLlama-34B achieved 48.8% pass@1 on HumanEval - CodeLlama-34B-Python achieved 53.7% pass@1 on HumanEval We have fine-tuned both models on a proprietary dataset of ~80k high-quality programming problems and solutions. Instead of code completion examples, this dataset features instruction-answer pairs, setting it apart structurally from HumanEval. We trained the Phind models over two epochs, for a total of ~160k examples. LoRA was not used — both models underwent a native fine-tuning. We employed DeepSpeed ZeRO 3 and Flash Attention 2 to train these models in three hours using 32 A100-80GB GPUs, with a sequence length of 4096 tokens. Furthermore, we applied OpenAI's decontamination methodology to our dataset to ensure valid results, and found no contaminated examples. The methodology is: - For each evaluation example, we randomly sampled three substrings of 50 characters or used the entire example if it was fewer than 50 characters. - A match was identified if any sampled substring was a substring of the processed training example. For further insights on the decontamination methodology, please refer to Appendix C of OpenAI's technical report. Presented below are the pass@1 scores we achieved with our fine-tuned models: - Phind-CodeLlama-34B-v1 achieved 67.6% pass@1 on HumanEval - Phind-CodeLlama-34B-Python-v1 achieved 69.5% pass@1 on HumanEval Note on GPT-4 According to the official technical report in March, OpenAI reported a pass@1 score of 67% for GPT-4's performance on HumanEval. Since then, there have been claims reporting higher scores. However, it's essential to note that there hasn't been any concrete evidence pointing towards an enhancement in the model's coding abilities since then. It's also crucial to highlight that these elevated figures lack the rigorous contamination analysis that the official statistic underwent, making them less of a reliable comparison. As a result, we consider 67% as the pass@1 score for GPT-4. Download We are releasing both models on Huggingface for verifiability and to bolster the open-source community. We welcome independent verification of results. Phind-CodeLlama-34B-v1: https://ift.tt/Qmw5nDN Phind-CodeLlama-34B-Python-v1: https://ift.tt/VmWcrbA We'd love to hear your thoughts! Best, The Phind Team https://ift.tt/aWsm6SC August 26, 2023 at 03:38AM