Paving the Road to Vulkan on Asahi Linux

Hey HN, we’re the cofounders of bloop (<a href="https:&#x2F;&#x2F;bloop.ai&#x2F;">https:&#x2F;&#x2F;bloop.ai&#x2F;</a>), a code search engine which combines semantic search with GPT-4 to answer questions. We let you search your private codebases either the traditional way (regex or literal) or via semantic search, ask questions in natural language thanks to GPT-4, and jump between refs&#x2F;defs with precise code navigation. Here’s a quick demo: <a href="https:&#x2F;&#x2F;www.loom.com&#x2F;share&#x2F;8e9d59b88dd2409482ec02cdda5b9185" rel="nofollow">https:&#x2F;&#x2F;www.loom.com&#x2F;share&#x2F;8e9d59b88dd2409482ec02cdda5b9185</a>Traditional code search tools match the terms in your query against the codebase, but often you don’t know the right terms to start with, e.g. ‘Which library do we use for model inference?’ (These types of questions are particularly common when you’re learning a new codebase.) bloop uses a combination of neural semantic code search (comparing the meaning - encoded in vector representations - of queries and code snippets) and chained LLM calls to retrieve and reason about abstract queries.Ideally, a LLM could answer questions about your code directly, but there is significant overhead (and expense) in fine-tuning the largest LLMs on private data. And although they’re increasing, prompt sizes are still a long way off being able to fit a whole organisation’s codebase.We get around these limitations with a two-step process. First, we use GPT-4 to generate a keyword query which is passed to a semantic search engine. This embeds the query and compares it to chunks of code in vector space (we use Qdrant as our vector DB). We’ve found that using a semantic search engine for retrieval improves recall, allowing the LLM to retrieve code that doesn’t have any textual overlap with the query but is still relevant. Second, the retrieved code snippets are ranked and inserted into a final LLM prompt. We pass this to GPT-4 and its phenomenal understanding of code does the rest.Let’s work through an example. You start off by asking ‘Where is the query parsing logic?’ and then want to find out ‘Which library does it use?’. We use GPT-4 to generate the standalone keyword query: ‘query parser library’, which we then pass to a semantic search engine that returns a snippet demonstrating the parser in action: ‘let pair = PestParser::parse(Rule::query, query);’. We insert this snippet into a prompt to GPT-4, which is able to work out that pest is the library doing the legwork here, generating the answer ‘The query parser uses the pest library’.You can also filter your search by repo or language - What’s the readiness delay repo:myApp lang:yaml. GPT-4 will generate an answer constrained to the respective repo and language.We also know that LLMs are not always (at least not yet) the best tool for the job. Sometimes you know exactly what you’re looking for. For this, we’ve built a fast, trigram index based regex search engine based on Tantivy. Because of this, bloop is fast at traditional search too. For code navigation, we’ve built a precise go-to-ref&#x2F;def engine based on scope resolution that uses Tree-sitter.bloop is fully open-source. Semantic search, LLM prompts, regex search and code navigation are all contained in one repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;bloopAI&#x2F;bloop">https:&#x2F;&#x2F;github.com&#x2F;bloopAI&#x2F;bloop</a>.Our software is standalone and doesn’t run in your IDE. We were originally IDE-based but moved away from this due to constraints on how we could display code to the user.bloop runs as a free desktop app on Mac, Windows and Linux: <a href="https:&#x2F;&#x2F;github.com&#x2F;bloopAI&#x2F;bloop&#x2F;releases">https:&#x2F;&#x2F;github.com&#x2F;bloopAI&#x2F;bloop&#x2F;releases</a>. On desktop, your code is indexed with a MiniLM embedding model and stored locally, meaning at index time your codebase stays private. Indexing is fast, except on the very largest repos (GPU indexing coming soon). ‘Private’ here means that no code is shared with us or OpenAI at index time, and when a search is made only relevant code snippets are shared to generate the response. (This is more or less the same data usage as Copilot).We also have a paid cloud offering for teams ($12 per user per month). Members of the same organisation can search a shared index hosted by us.We’d love to hear your thoughts about the product and where you think we should take it next, and your thoughts on code search in general. We look forward to your comments!

Launch HN: Bloop (YC S21) – Code Search with GPT-4

A world to win: WebAssembly for the rest of us

Doors I touched today (1999)

Spack – scientific software package manager for supercomputers, Linux, and macOS

Chronology Clock

Why use Rust on the back end?

Hi HN, we’re Nicolas, Nebyou, and Robert and we’re building Lume (<a href="https:&#x2F;&#x2F;lume.ai">https:&#x2F;&#x2F;lume.ai</a>). Lume uses AI to generate custom data integrations. We transform data between any start and end schema and pipe the data directly to your desired destination. There’s a demo video here: <a href="https:&#x2F;&#x2F;www.loom.com&#x2F;share&#x2F;bed137eb38884270a2619c71cebc1213" rel="nofollow">https:&#x2F;&#x2F;www.loom.com&#x2F;share&#x2F;bed137eb38884270a2619c71cebc1213</a>.Companies spend countless engineering hours manually transforming data for custom integrations, or pay large amounts to consulting firms to do it for them. Engineers have to work through massive data schemas and create hacky scripts to transform data. Dynamic schemas from different clients or apps require custom integration pipelines. Many non-tech companies are even still relying on schemas from csv and pdf file formats. Days, weeks, and even months are spent just building integrations.We ran into this problem first-hand as engineers: Nebyou during his time as a ML engineer at Opendoor, where he spent months manually creating data transformations, while Nicolas did the same at his time working at Apple Health. Talking to other engineers, we learned this problem was everywhere. Because of the dynamic and one-off nature of different data integrations, it has been a challenging problem to automate. We believe that with recent improvements in LLMs (large language models), automation has become feasible and now is the right time to tackle it.Lume solves this problem head-on by generating data transformations, which makes the integration process 10x faster. This is provided through a self-serve managed platform where engineers can manage and create new data integrations.How it works: users can specify their data source and data destination, both of which specify the desired data formats, a.k.a. schemas. Data source and destinations can be specified through our 300+ app connectors, or custom data schemas can be connected by either providing access to your data warehouse, or a manual file upload (csv, json, etc) of your end schema. Lume, which includes AI and rule-based models, creates the desired transformation under the hood by drafting the necessary SQL code, and deploys it to your destination.At the same time, engineers don’t want to rely on low- or no-code tools without visibility under the hood. Thus, we also provide features to ensure visibility, confidence, and editability of each integration: Data Preview allows you to view samples of the transformed data, SQL Editor allows you to see the SQL used to create the transformation and to change the assumptions made my Lume’s model, if needed (most of the time, you don’t!). In addition, Lineage Graph (launching soon) shows you the dependencies of your new integration, giving more visibility for maintenance.Our clients have two primary use cases. One common use case is to transform data source(s) into one unified ontology. For example, you can create a unified schema between Salesforce, Hubspot, Quickbooks, and Pipedrive in your data warehouse. Another common use case is to create data integrations between external apps, such as custom syncs between your SaaS apps. For example, you can create an integration directly between your CRM and BI tools.The most important thing about our solution is our generative system: our model ingests and understands your schemas, and uses that to generate transformations that map one schema to another. Other integration tools, such as Mulesoft and Informatica, ask users to manually map columns between schemas—which takes a long time. Data transformation tools such as dbt have improved the data engineering process significantly (we love dbt!) but still require extensive manual work to understand the data and to program. We abstract all of this and do all the transformations for our customers under the hood - which reduces the time taken to manually map and engineer these integrations from days&#x2F;weeks to minutes. Our solution handles the truly dynamic nature of data integrations.We don’t have a public self-serve option yet (sorry!) because we’re at the early stage of working closely with specific customers to get their use cases into production. If you’re interested in becoming one of those, we’d love to hear from you at <a href="https:&#x2F;&#x2F;lume.ai">https:&#x2F;&#x2F;lume.ai</a>. Once the core feature set has stabilized, we’ll build out the public product. In the meantime, our demo video shows it in action: <a href="https:&#x2F;&#x2F;www.loom.com&#x2F;share&#x2F;bed137eb38884270a2619c71cebc1213" rel="nofollow">https:&#x2F;&#x2F;www.loom.com&#x2F;share&#x2F;bed137eb38884270a2619c71cebc1213</a>.We currently charge a flat monthly fee that varies based on the quantity of data integrations. In the future, we plan on having more transparent pricing that’s made up of a fixed platform fee + compute-based charges. To not have surprise charges, we currently run the compute in your data warehouse.We’re looking forward to hearing any of your comments, questions, ideas, experiences, and feedback!

Launch HN: Lume (YC W23) – Generate custom data integrations with AI

The genie escapes: Stanford copies the ChatGPT AI for less than $600

Argbash – Bash Argument Parsing Code Generator

Cyclists now outnumber motorists in City of London

I&#x27;ve been playing with the idea of an LLM prompt that causes the model to generate and return a new prompt. <a href="https:&#x2F;&#x2F;github.com&#x2F;andyk&#x2F;recursive_llm">https:&#x2F;&#x2F;github.com&#x2F;andyk&#x2F;recursive_llm</a>The idea I&#x27;m starting with is to implement recursion using English as the programming language and GPT as the runtime.It’s kind of like traditional recursion in code, but instead of having a function that calls itself with a different set of arguments, there is a prompt that returns itself with specific parts updated to reflect the new arguments.Here is a prompt for infinitely generating Fibonacci numbers:&gt; You are a recursive function. Instead of being written in a programming language, you are written in English. You have variables FIB_INDEX = 2, MINUS_TWO = 0, MINUS_ONE = 1, CURR_VALUE = 1. Output this paragraph but with updated variables to compute the next step of the Fibbonaci sequence.Interestingly, I found that to get a base case to work I had to add quite a bit more text (i.e. the prompt I arrived at is more than twice as long <a href="https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;andyk&#x2F;recursive_llm&#x2F;main&#x2F;prompt_fibonnaci_include_math.txt" rel="nofollow">https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;andyk&#x2F;recursive_llm&#x2F;main&#x2F;p...</a>)

Show HN: Recursive LLM Prompts

I built this customizable literature-based K-12 homeschool curriculum, based on my experience as a homeschool parent. It&#x27;s designed especially for intellectually curious kids who love to read.One of the main benefits of homeschooling is the ability to design customized programs of study that let kids learn at their level of challenge in each subject. But since designing custom curricula from scratch requires a huge time commitment and familiarity with children&#x27;s literature and academic materials, most homeschooling parents don&#x27;t take advantage of this potential and instead opt for prepackaged curricula.Great Books Homeschool eliminates a lot of the work involved in designing a complete and rigorous curriculum for homeschooled students. The website generates a default program of study for each student, then helps parents customize it. Transcripts and other records are generated automatically.Pricing is normally subscription based, but we&#x27;re offering complimentary access for twelve months to the first 50 users who sign up for our beta testing program. In return, beta testers are requested to complete a monthly questionnaire about their experience with the curriculum.If you would like to participate in the beta testing program, please first create a free trial account at <a href="https:&#x2F;&#x2F;www.greatbookshomeschool.com" rel="nofollow">https:&#x2F;&#x2F;www.greatbookshomeschool.com</a>. Once signed in, go to <a href="https:&#x2F;&#x2F;www.greatbookshomeschool.com&#x2F;parent&#x2F;beta-application?via=hn" rel="nofollow">https:&#x2F;&#x2F;www.greatbookshomeschool.com&#x2F;parent&#x2F;beta-application...</a> and complete the application form.Questions and comments are welcome!

Show HN: Great Books Homeschool beta program

JEP 442: Foreign Function and Memory API (Third Preview)

Anyone else noticing this while editing an email? It seems just crazy.

Tell HN: MailChimp blacklists your IP if you open the browser's dev tools

When can two TCP sockets share a local address?

Lessons from a Pessimist: Make Your Pessimism Productive

Cesium-137 missing and found in junk yard in Thailand

As a developer, I recently encountered challenges with GRUB and discovered I lacked knowledge about my computer&#x27;s boot process. I realized terms like EFI partition, MBR, GRUB, and Bootloader were unfamiliar to me and many of my colleagues. I&#x27;m seeking introductory and easy-to-understand resources to learn about these concepts. Any recommendations would be appreciated!