Show HN: Mr. Graph. A graph deifnition and execution library for Python https://ift.tt/39BEvpG

Show HN: Mr. Graph. A graph deifnition and execution library for Python What: Mr. Graph is a python library designed to make composing graphs of sync and async functions easy! Use google style docstrings to automagically create dataclasses and chain together function calls into graphs. Why: I like the design of Dagster, but not the latency. For apps and systems engineering, sometimes I want to compose a graph out of regular python functions. I don;t need all the heavy machinery that comes with a full workflow engine. Current features: - Use with either async or sync functions - Uses google style doc strings to name return values. - Creates dataclasses for each function's output. - Can infer pipelines from input and output signatures - All directed acyclic graph layouts supported. linear, fan-in, fan-out. Future Features: - Better examples for use with async calls (like LLMs) - Splitting dataclasses, better error handling, logging improvements. This is under active development. Any feedback, interest, or contributions are appreciated. Thanks! https://ift.tt/Bu2yJrw March 15, 2023 at 10:00PM

Show HN: Discontent – Extension to combat garbage search engine results https://ift.tt/euomATB

Show HN: Discontent – Extension to combat garbage search engine results Creator here. In a nutshell this extension is a "Like / Dislike" system but for website results. I miss the days of things like the YouTube dislike bar, where you can quickly assess if something is good or not. Currently sitting at ~90 users. To get it off the ground I've scraped the last year of HN to make a set of good links, and used a few content farm blacklists to make a set of bad links. Right now it's semi-useful and should only get better with time. There are some simple measures in place to prevent spam & abuse, but will cross that bridge if it ever comes. All feedback welcome! https://ift.tt/TQ5o1Mj March 15, 2023 at 07:01PM

Show HN: Gamaddy – Play Online Games https://ift.tt/f96QZbg

Show HN: Gamaddy – Play Online Games https://gamaddy.com/ March 15, 2023 at 01:01PM

Show HN: Whatdoesthiscodedo.com – AI explanations for other people’s code https://ift.tt/HfJiypb

Show HN: Whatdoesthiscodedo.com – AI explanations for other people’s code https://ift.tt/LdPH7CE March 15, 2023 at 06:03AM

Show HN: Built a blog using Rust and Axum https://ift.tt/g8WbuYo

Show HN: Built a blog using Rust and Axum https://ift.tt/JD1A86I March 14, 2023 at 10:49PM

Show HN: Potash – Malware Proximity Search Engine https://ift.tt/GLlVjcT

Show HN: Potash – Malware Proximity Search Engine I wrote a search engine that ingests malware TLSH hashes from abuse.ch and provides a proximity search engine in order to find "close" malwares to yours. Comes handy if you want to classify a Malware that's not on VT or a malware that you only have the hash, but want to download a close enough sample. It works as a CLI app or a ReST API https://ift.tt/WAo9ZyJ March 14, 2023 at 02:01PM

Show HN: Using GPT-3 and Whisper to save 40% of doctors’ time https://ift.tt/hEpO8du

Show HN: Using GPT-3 and Whisper to save 40% of doctors’ time Hey HN, We're Alex, Martin and Laurent. We previously founded Wit.ai (W14), which we sold to Facebook in 2015. Since 2019, we've been working on Nabla (https://www.nabla.com), an intelligent assistant for health practitioners. When GPT-3 was released in 2020, we investigated it's usage in a medical context[0], to mixed results. Since then we’ve kept exploring opportunities at the intersection of healthcare and AI, and noticed that doctors spend am awful lot of time on medical documentation (writing clinical notes, updating their EHR, etc.). Today, we're releasing Nabla Copilot, a Chrome extension generating clinical notes from video consultations, to address this problem. You can try it out, without installation nor sign up, on our demo page: https://ift.tt/3XKzLtC Here’s how it works under the hood: - When a doctor starts a video consultation, our Chrome extension auto-starts itself and listens to the active tab as well as the doctor’s microphone. - We then transcribe the consultation using a fine-tuned version of Whisper. We've trained Whisper with tens of thousands of hours of medical consultation and medical terms recordings, and we have now reached an error rate which is 3× lower than Google's Speech-To-Text. - Once we have the transcript, we feed it to a heavily trained GPT-3, which generates a clinical note. - We finally return the clinical note to the doctor through our Chrome extension, the doctor can copy it to their EHR, and send a version to the patient. This allows doctors to be fully focused on their consultation, and saves them a lot time. Next, we want to make this work for in-person consultation. We also want to extract structured data (in the FHIR standard) from the clinical note, and feed it to the doctor’s EHR so that it is automatically added to the patient's record. Happy to further discuss technical details in comments! --- [0]: https://ift.tt/2Lj4Pu3 March 14, 2023 at 07:46PM