Show HN: I made danluu's blog easier to read https://ift.tt/yjNrv7R

Show HN: I made danluu's blog easier to read Hi, I'm Alex! I believe most of the knowledge is nowadays stored and hidden in personal blogs. I have a list of blogs that I read recurrently, and I have benefited myself a lot from this practice. One of the blogs that are usually recommended is the one by Dan Luu. Dan writes about a variety of topics in his blog, and I usually enjoy what he writes. But besides from the content Dan's blog stands out for the complete lack of CSS. IMHO this makes the content difficult to read (it's like reading text from a windows text editor). I believe more people will read and enjoy his blog if a pinch of CSS was added to the blog, so I've taken the liberty to enhance the reading experience. I wrote a script that periodically checks Dan's blog and publish the content in a static webpage (hosted using GitHub Pages). Regarding the CSS I just copied the CSS proposed in https://ift.tt/l0HuyjW and changed the font family. Give it a look and see what you think! Enjoy the improved readability. P.S. The code that does all this magic might not win any awards for beauty, but it gets the job done. If time permits, I "promise" to tidy it up in the future. Your understanding is appreciated! https://ift.tt/64I2Xic August 24, 2023 at 03:48AM

Show HN: Dataherald AI – Natural Language to SQL Engine https://ift.tt/GF2zWJy

Show HN: Dataherald AI – Natural Language to SQL Engine Hi HN community. We are excited to open source Dataherald’s natural-language-to-SQL engine today ( https://ift.tt/iv1Ghet ). This engine allows you to set up an API from your structured database that can answer questions in plain English. GPT-4 class LLMs have gotten remarkably good at writing SQL. However, out-of-the-box LLMs and existing frameworks would not work with our own structured data at a necessary quality level. For example, given the question “what was the average rent in Los Angeles in May 2023?” a reasonable human would either assume the question is about Los Angeles, CA or would confirm the state with the question asker in a follow up. However, an LLM translates this to: select price from rent_prices where city=”Los Angeles” AND month=”05” AND year=”2023” This pulls data for Los Angeles, CA and Los Angeles, TX without getting columns to differentiate between the two. You can read more about the challenges of enterprise-level text-to-SQL in this blog post I wrote on the topic: https://ift.tt/0KOQyzd... Dataherald comes with “batteries-included.” It has best-in-class implementations of core components, including, but not limited to: a state of the art NL-to-SQL agent, an LLM-based SQL-accuracy evaluator. The architecture is modular, allowing these components to be easily replaced. It’s easy to set up and use with major data warehouses. There is a “Context Store” where information (NL2SQL examples, schemas and table descriptions) is used for the LLM prompts to make the engine get better with usage. And we even made it fast! This version allows you to easily connect to PG, Databricks, BigQuery or Snowflake and set up an API for semantic interactions with your structured data. You can then add business and data context that are used for few-shot prompting by the engine. The NL-to-SQL agent in this open source release was developed by our own Mohammadreza Pourreza, whose DIN-SQL algorithm is currently top of the Spider ( https://ift.tt/KOI4kvm ) and Bird ( https://ift.tt/KRl3osc ) NL 2 SQL benchmarks. This agent has outperformed the Langchain SQLAgent anywhere from 12%-250%.5x (depending on the provided context) in our own internal benchmarking while being only ~15s slower on average. Needless to say, this is an early release and the codebase is under swift development. We would love for you to try it out and give us your feedback! And if you are interested in contributing, we’d love to hear from you! https://ift.tt/iv1Ghet August 24, 2023 at 12:08AM

Show HN: Gentrace – evaluation and observability for generative AI https://ift.tt/mwcUKCI

Show HN: Gentrace – evaluation and observability for generative AI Hi HN, Gentrace is our new evaluation and observability tool for generative AI (open beta). Generative pipelines are hard to evaluate because outputs are subjective. Lots of developers end up just doing “gut checks” on a few inputs before shipping changes, or they build up a spreadsheet of test cases that they manually run through the pipeline. Some companies outsource filling out the spreadsheet. However, in any of these cases, you end up with a very slow and expensive process for evaluation. At one point, we did this too. Gentrace is the result of a pivot; it was an internal tool we used to automatically grade new PRs as developers shipped changes to generative pipelines that other people thought might be useful. Gentrace makes pre-production testing of generative pipelines continuous and nearly instantaneous. In Gentrace, you: - Import and/or construct suites of test data - Use a combination of AI and heuristic evaluators to grade for quality, hallucination, safety, etc - Use our interface to correct automated grades or add your own (yourself or a member of your team) Gentrace integrates at a code level for evaluation, meaning we test your generative AI pipeline the way you would test normal code. This allows you to test more than just prompt changes; for example, you can compare models (eg Claude 2 vs GPT-4 vs GPT 3.5 vs Llama 2) or see the effects of additional chained steps (”Rewrite the previous answer in the following tone:”). Here’s a video overview that goes into a bit more detail: https://youtu.be/XxgDPSrTWIw In production, Gentrace observes for speed, cost, and data flow. It also shows real user feedback as well. We do this by integrating via our SDK at a code level; Gentrace does not proxy requests. Soon, we’ll allow you to convert production data into test cases, allowing customer support to turn bad production generations into “failing tests” for AI teams to make pass. We process interim steps and multiple outputs as well, helping evaluate agent flows / chains where the “last output” isn’t always the only thing that matters. There’s been a lot of observability tools published recently. We differ from those by focusing more strongly on blending observability with strong evaluation and by using an SDK rather than a “man-in-the-middle” approach to capturing data (ie Gentrace can be down and your request to OpenAI will still succeed). Within the evaluation landscape, we differentiate by integrating with code (see above for benefits) for capturing generative outputs and by providing a customizable UI workflow for building evaluators. In Gentrace, you start with off-the-shelf automated evaluators and then customize them to your specific task. You also build and run new evaluators on old generative outputs. Finally, you easily override automated evaluators and/or blend automated evaluation with evaluation by humans on your team. We also focus on being suitable for business use. We are SOC 2 Type 1 compliant (Type 2 coming shortly), have robust legal documentation around data processing, security, and privacy, and have already passed several vendor legal and security reviews at large technology companies. Our standard usage-based pricing is available on the website: https://ift.tt/w6Xa1Ve If you are building features with generative AI, we would love to get your feedback. You can self-serve sign up (without a credit card) for a 14 day trial here: https://gentrace.ai/ We’re available right here for feedback and questions. We’re also available at support@gentrace.ai. Best, Doug, Vivek, and Daniel https://gentrace.ai August 23, 2023 at 10:08PM

Show HN: Pip install inference, open source computer vision deployment https://ift.tt/cBaQbjJ

Show HN: Pip install inference, open source computer vision deployment Deploying vision models is time consuming and tedious. Setting up dependencies. Fixing conflicts. Configuring TRT acceleration. Flashing (and re-flashing) NVIDIA Jetsons. A streamlined, developer-friendly solution for inference is needed. We, the Roboflow team, have been hard at work open sourcing Inference, an open source vision deployment solution. Our solution is designed with developers in mind, offering a HTTP-based interface. Run models on your hardware without having to write architecture-specific inference code. Here's a demo showing how to go from a model to GPU inference on a video of a football game in ~10 minutes: https://www.youtube.com/watch?v=at-yuwIMiN4 Inference powers millions of daily API calls for global sports broadcasts, one of the world’s largest railways, a leading electric car manufacturer, and multiple other Fortune 500 companies, along with countless hackers’ hobby and research projects. Inference works in Docker and supports CPU (ARM and x86), NVIDIA GPU, and TRT. Inference manages dependencies and the environment. All you need to do is make HTTP requests to the server. YOLOv5, YOLOv8, YOLACT, CLIP, SAM, and other popular vision models are supported (some models need to be hosted on Roboflow first, see the docs; we're working on bring your own model weights!). Try it out and tell us what you think! https://ift.tt/xJ3F4lT August 23, 2023 at 04:34PM

Show HN: To mute words on Twitter in batches, I created a browser extension https://ift.tt/vJEYPIa

Show HN: To mute words on Twitter in batches, I created a browser extension Hello HN community :) For a while now I've been watching my Twitter feed fill up with more and more crap. The fact that it's now possible to monetise your tweets has made things even crappier. At the same time, adding words to mute is a pain. First you have to find the option, buried deep in Twitter's settings, and then you have to add them one by one. So I came up with the idea of writing a little browser extension that lets you add lists of muted words, which can come from more or less anywhere, as long as they're in a certain format (a multi-line text file or a JSON array). The extension doesn't collect any data, you don't need an account to use it, and you can store your lists anywhere (although I'd recommend Github gist or Pastebin). To be honest, I made this mainly as an exercise to learn how a browser extension works and how to make one, but if it's useful to people, that's great! Feel free to let me know what you think and give it a try. If there's ever an audience for it, I'm thinking of taking it further by adding lists of people to mute, extracting your existing list of muted words from Twitter, etc.If you have any other ideas for development, I'd love to hear from you. https://ift.tt/nwySMKL August 23, 2023 at 05:13PM

Show HN: My New Portfolio Update https://ift.tt/Cpr6135

Show HN: My New Portfolio Update https://anasdew.com/ August 23, 2023 at 11:49AM

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://ift.tt/6sNwf0u

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://ift.tt/80myJsG August 23, 2023 at 09:26AM