Introducing Superalignment
87 by tim_sw | 84 comments on Hacker News.
Wednesday, July 5, 2023
New top story on Hacker News: Ask HN: What boosted your confidence as a new programmer?
Ask HN: What boosted your confidence as a new programmer?
6 by optbuild | 5 comments on Hacker News.
When anyone starts out in a new craft, even after grasping the fundamentals of the tools they are quite shaky and low on confidence until they have a significant experience in doing something that ultimately ramps up their confidence in their craftsmanship. Similar things happen with novice programmers when they start out. Then they read a beautiful codebase which they can fully understand and replicate, or build a project from scratch, or read a book or take a class on a subject. And their confidence is tremendously boosted thereafter. What was it for you? How did you gain this confidence to take the first step from being a tinkerer to being a skilled craftman?
6 by optbuild | 5 comments on Hacker News.
When anyone starts out in a new craft, even after grasping the fundamentals of the tools they are quite shaky and low on confidence until they have a significant experience in doing something that ultimately ramps up their confidence in their craftsmanship. Similar things happen with novice programmers when they start out. Then they read a beautiful codebase which they can fully understand and replicate, or build a project from scratch, or read a book or take a class on a subject. And their confidence is tremendously boosted thereafter. What was it for you? How did you gain this confidence to take the first step from being a tinkerer to being a skilled craftman?
Tuesday, July 4, 2023
Monday, July 3, 2023
New top story on Hacker News: Ask HN: Who wants to be hired? (July 2023)
Ask HN: Who wants to be hired? (July 2023)
37 by whoishiring | 131 comments on Hacker News.
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Readers: please only email these addresses to discuss work opportunities.
37 by whoishiring | 131 comments on Hacker News.
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Readers: please only email these addresses to discuss work opportunities.
New top story on Hacker News: Show HN: JobLens AI-powered job search for 'Who Is Hiring'
Show HN: JobLens – AI-powered job search for 'Who Is Hiring'
4 by hubraumhugo | 0 comments on Hacker News.
There are existing HN job aggregators, but I thought we could take it a step further. Inspired by an insightful comment on a previous thread ( https://ift.tt/V1DjsGJ ), I built a tool that aggregates job postings and intelligently categorizes them based on user-specific preferences: * Country and remote work preferences * Employer type (e.g., startup, corporation, government) * Industry * Technologies used * Role type (developer, architect, product owner, etc.) * Salary range (where available) One of the superpowers of LLMs is reformatting information from any format X to any other format Y. We leverage this to map all the unstructured job postings into the same unified structure. The new GPT functions feature and the extended context windows are really helpful for this. Instead of having to build a custom NER pipeline, it works very well with GPT out-of-the box. One challenge is keeping the filters consistent and merging of duplicates. Embeddings help with that. What's next: * Integrate additional sources. We can generate web scrapers and data processing steps on the fly that extract and transform data into the same structure. * Add location distance filters. * Expand beyond jobs to monitor personalized data like events or real estate. Imagine using AI to rate local events from multiple sources based on your preferences, considering factors like your interests and distance from home. * Smaller improvements based on your feedback :)
4 by hubraumhugo | 0 comments on Hacker News.
There are existing HN job aggregators, but I thought we could take it a step further. Inspired by an insightful comment on a previous thread ( https://ift.tt/V1DjsGJ ), I built a tool that aggregates job postings and intelligently categorizes them based on user-specific preferences: * Country and remote work preferences * Employer type (e.g., startup, corporation, government) * Industry * Technologies used * Role type (developer, architect, product owner, etc.) * Salary range (where available) One of the superpowers of LLMs is reformatting information from any format X to any other format Y. We leverage this to map all the unstructured job postings into the same unified structure. The new GPT functions feature and the extended context windows are really helpful for this. Instead of having to build a custom NER pipeline, it works very well with GPT out-of-the box. One challenge is keeping the filters consistent and merging of duplicates. Embeddings help with that. What's next: * Integrate additional sources. We can generate web scrapers and data processing steps on the fly that extract and transform data into the same structure. * Add location distance filters. * Expand beyond jobs to monitor personalized data like events or real estate. Imagine using AI to rate local events from multiple sources based on your preferences, considering factors like your interests and distance from home. * Smaller improvements based on your feedback :)