Here's mine fully deployed, https://hackernewsanalyzer.com/. I use it daily and have some users. ~99.7% LLM code. About 1 hour to first working prototype then another 40 hours to get it polished and complete to current state.
It shows, quite an interesting wrapper over GPT with unauthorized access to prompting it you assembled there ;) Very much liked the part where it makes 1000 requests pulling 1000 comments from the firebase to the client and then shoots them back to GPT via supabase
41 hours total of prompting, looking at code diffs, reverting, reprompting, and occasional direct code commits. I do review the full code changes nearly every step of the way and often iterate numerous times until I'm satisfied with the resulting code approach.
Have you tried to go back to the old way, maybe just as an experiment, to see how much time you are actually saving? You might be a little surprised! Significant "reprompting" time to me indicates maybe a little too much relying on it rather than leading by example. Things are much faster in general if you find the right loop of maybe using Claude for like 15%-20% of stuff instead of 99.7%. You wouldn't give your junior 99.7% ownership of the app unless they were your only person, right? I find spending time thinking through certain things by hand will make you so much more productive, and the code will generally be much better quality.
I get that like 3 years ago we were all just essentially proving points building apps completely with prompts, and they make good blog subjects maybe, but in practice they end up being either fragile novelties or bloated rat's nests that end up taking more time not less.
I’ve done things in days that in the before times would have took me months. I don’t see how you can make that time difference up.
I have at least one project where I can make that direct comparison - I spent three months writing something in the language I’ve done most of my professional career in, then as a weekend project I got ChatGPT to write it from scratch in a different language I had never used before. That was pre-agentic tools - it could probably be done in an afternoon now.
I'm not a fulltime developer, but manage a large dev team now. So, this project is basically beyond my abilities to code myself by hand. Pre llm, I would expect in neighborhood of 1.5-2 months for a capable dev on my team to produce this and replicate all the features.
I taught English in Seoul for a year in '02/'03. bang = room. There was (maybe still is?) a PC bang on every block or two pretty much. I'm sure I went at least 100 times. Great way to kill some time playing counter-strike for me and dabbling in starcraft. It was maybe $1.50/hr at the time. For a much better PC, nice chair, pre-installed games and snacks available.
This article bummed me out. I think this analogy of popular digital content being the 'junk food' of the brain is correct and the negative effects will, yet again, accrue disproportionately to the poor and less privileged in society. Sadly, it looks inevitable with no mechanism to prevent or counter it.
not OP, but for the "unique identifiers", you can think of it like the footnote style of markdown links. Most of these models are fine-tuned to do markdown well, and a short identifier is less likely to be hallucinated (my philosophy anyway), so it usually works pretty well. For the examples, something like this can work
Instead of having the LLM generate the links couldn’t you use a combination of keyword matching and similarity on the model output and the results to automatically add citations? You could use a smaller NLP model or even a rule based system to extract entities or phrases to compare. I’m sure this is already being done by bing for example.
You definitely can do that. It’s just sometimes simpler to dump lots of stuff in context and then check it wasn’t made up.
It like the idea of using markdown footnotes. I think that would word well - ChatGPT does handle markdown really well.
Great resource and very well written articles. I'm always curious how these come to be when done really well. I wish we could generate high quality, useful, correct, internal documentation like this at my company, but I've never figured out how to get that done in practice. The people that know the concepts are not natural/gifted writers, or at least wouldn't be motivated or prioritize doing this. Even if they did, the style/tone/depth would vary greatly. For these msft docs, they somehow achieve consistent tone, depth, and quality/correctness across so many domains and I just don't know how that's achieved.
BlackRock – Aladdin Wealth | New York, NY | Full-time ONSITE, VISA | Data Engineer Manager
I’m looking for the right person to lead a small data engineering team, which is part of a larger (50+ person) global engineering team building Aladdin Wealth (https://www.blackrock.com/aladdin/products/aladdin-wealth), a revenue-generating FinTech SaaS product for the wealth management industry. We apply BlackRock's sophisticated risk analytics to millions of individual investors' portfolios to help them and their financial advisors create better portfolios. We have live production clients in 15+ countries around the world and we process and analyze millions of real customer portfolios on a daily basis.
You will have the opportunity to dive deep into the business, learning Aladdin, portfolio management, investment analytics (factor risk models, VaR, tracking error, historical scenarios, etc), and the wealth management industry. I lead the global engineering team and this role will report directly to me. Full job descriptions and application instructions at the below link, but you can reach out to me directly if interested: msahn@blackrock.com
* Manage and lead a small team of Data Engineers working primarily in Python, but with some R and Perl, as well
* Be a hands-on engineer, developing and releasing code, yourself, and reviewing PRs from your team
* Work closely with Product Managers and Implementation team to build robust and efficient data pipelines through automation
* Work with other engineering team leads and partners to continuously improve operational processes and procedures
* Design and develop data analysis tools to generate actionable insights based on customer and team generated requirements
Note for VISA applicants: We can only consider applicants that are already in the US with existing work authorization (H1B transfers, OPT, etc).
On REMOTE work: We do not offer fully remote work, so you must be in the US already and able to work from our NYC office at least 3 days a week. You can work remotely from home up to 2 days per week.
BlackRock – Aladdin Wealth | New York, NY / San Francisco, CA | Full-time ONSITE, VISA | Front-end Software Engineer / Back-end Software Engineer
We have 4 positions available immediately on my team building Aladdin Wealth (https://www.blackrock.com/aladdin/products/aladdin-wealth), a revenue-generating FinTech SaaS product for the wealth management industry. We apply BlackRock's sophisticated risk analytics to millions of individual investors' portfolios to help them and their financial advisors create better portfolios. We have live production clients in countries around the world and we process and analyze millions of real customer portfolios using Spark on a daily basis.
The front-end roles are focused on our web apps building out new features and better user experiences in React framework. We're looking for people who are super proficient in React/ES6/TypeScript and want to work with and leverage modern tools and techniques to the fullest. Front-end team also works on and owns various Java-based application servers, so there is a full-stack component, as well, but it leans more to the frontend side.
The back-end roles are for experienced engineers to architect, develop, and deploy scalable services and APIs. We work with a wide array of technologies (Java, Scala, Kotlin, Spark, Hadoop, Cassandra, Solr, Python), but solid Java is the backbone.
In all of the roles, diving deep into the business, learning Aladdin, portfolio management, investment analytics (factor risk models, VaR, tracking error, historical scenarios, etc), and the wealth management industry, will be a big part of your success. I lead the global team that is hiring these roles. Full job descriptions and application instructions at below links, but you can reach out to me directly if interested: msahn@blackrock.com
Note for VISA applicants: We can only consider applicants that are already in the US with existing work authorization (H1B transfers, OPT, etc).
On REMOTE work: We do not offer fully remote work, so you must be in the US already and able to work from NY or SF. Of course, we are working remotely during Covid, but expect to be at least partially in office this year.
BlackRock – Aladdin Wealth | New York, NY / San Francisco, CA / Atlanta, GA | Full-time ONSITE, VISA | Front-end Software Engineer / Senior Back-end Software Engineer / Data Engineer |
We have 5-7 positions available immediately on my team building Aladdin Wealth (https://www.blackrock.com/aladdin/products/aladdin-wealth), a revenue-generating FinTech SaaS product for the wealth management industry. We apply BlackRock's sophisticated risk analytics to millions of individual investors' portfolios to help them and their financial advisors create better portfolios. We have live production clients in countries around the world and we process and analyze millions of real customer portfolios using Spark on a daily basis.
The front-end roles are focused on our web apps building out new features and better user experiences in React framework. We're looking for people who are super proficient in React/ES6/TypeScript and want to work with and leverage modern tools and techniques to the fullest. Front-end team also works on and owns various Java-based application servers, so there is a full-stack component, as well, but it leans more to the frontend side.
The back-end roles are for experienced engineers to architect, develop, and deploy scalable services and APIs. We work with a wide array of technologies (Java, Scala, Kotlin, Spark, Hadoop, Cassandra, Solr, Python), but solid Java is the backbone.
There is one Data Engineering role (3-5 years experience) available in NYC. This role is focused on building process automation, data ETL, and some data science & analysis, primarily in Python with occasional R and Perl.
In all of the roles, diving deep into the business, learning Aladdin, portfolio management, investment analytics (factor risk models, VaR, tracking error, historical scenarios, etc), and the wealth management industry, will be a big part of your success. Reach out to me directly if interested. I lead the global team that is hiring these roles: msahn@blackrock.com. Full job descriptions and application instructions at below links for some roles, but not all have been posted externally.
Note for VISA applicants: We can only consider applicants that are already in the US with existing work authorization (H1B transfers, OPT, etc).
On REMOTE work: We do not offer fully remote work, so you must be in the US already and able to work from NY, SF, or ATL area. Of course, we are working remotely during Covid, but expect to be at least partially in office this year.
BlackRock – Aladdin Wealth | New York, NY | Full-time ONSITE, VISA | Front-end Software Engineer, Senior Back-end Software Engineer |
We have two positions available immediately on my team building Aladdin Wealth, a revenue-generating SaaS product for the wealth management industry. We apply BlackRock's sophisticated risk analytics, which are used to manage over $20 trillion of institutional money, to millions of individual investors' portfolios to help them and their Financial Advisors create better portfolios. We have live production clients in countries around the world who are servicing millions of end customers aided by our product. The front-end role will be focused immediately on our web apps building out new features and better user experience in React framework. We're looking for someone who is really proficient in React/ES6/TypeScript and wants to work with and leverage modern tools and techniques to the fullest. The back-end role is for a senior engineer to architect, develop, and deploy scalable services and APIs. We work with a wide array of technologies (Java, Scala, Spark, Hadoop, Cassandra, Solr, Python), but solid Java is definitely a must. In either role, diving into the business, learning Aladdin, investment analytics, the wealth management industry, etc will be a big part of your success, as well.
Reach out to me directly if interested. I lead the team that is hiring these roles: msahn@blackrock.com. Full job descriptions and application instructions at below links.
