jamifsud

I've been using Claude Code for weeks now and I've found it to be fantastic at writing / debugging tests unit / integ tests that don't require external context. Still needs some guidance of course but it's been a huge productivity improvement.

Unfortunately, I can't say the same for other types of tests like E2E tests. It makes sense why: CC doesn't have access to all of the context to determine what's going wrong. During an E2E test suite run it can't pause to look into the console, view whats on the page, look at the backend logs, etc. I tried writing some utilities to snapshot and log the state of parts of the page when a test failed and this did help a bit, but not enough to get the same productivity boost for other types of tests.

Has anyone had any luck with this? Any strategies to share?

I'm hearing about lots of alternatives lately: Comila, Rancher Desktop, Podman Desktop, OrbStack, etc.

Which one do folks like best?

Tangential question - what are people using their homelab for / what are some interesting or useful projects you've spun up on them? I've been thinking about setting one up but not 100% sure I'd find use out of it :)

Working on it, shoot me an email (joe at domain) would love to get your feedback on the format / contents!

Working on https://www.brief.news - a completely personalized daily newsletter on the topics you're interested in. We've just launched the ability to add custom topics, so you can create a newsletter on anything now!

I switched to HomePods for exactly this reason, Alexa was constantly upselling me on features and Amazon products. Threw it out.

We’re working toward exactly this with https://www.brief.news! We’ve got the ability to create custom topics in beta (I’m currently using it to follow Starship updates), happy to add you to the beta just shoot me an email (in profile).

Any plans for a Python SDK? We’re actively looking for a platform like this but our stack is TS / Python!

I’ve found GPT 3.5 to do a good job of this, not perfect but I bet with some more prompt engineering it could get really good.

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML

At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. Our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so our users will always have the most important updates about topics they care about. We have open roles for:

- Software developers: our tech stack is TypeScript / Node / React / Python

- Designers: we're creating a seamless, beautiful experience across desktop, native and web

- ML engineer: help us design build and deploy our first generation of recommendation and understanding systems

If you'd like to chat, email me at joe [at] upnext [dot] in!

There’s definitely a need here, love the category specific TLDs.

Thanks! We got a couple different formats available, check out the top stories format which is close to what you suggest. Would love to hear your thoughts on it! We’re considering making that the default.

Thanks!

A lot! We’re actively reducing that though by training our own specialized models. We’re seeing equal or better performance with curated datasets at > 10x cost reduction.

I'm building https://www.brief.news, an AI powered newsletter that condenses tens of thousands of news articles into a daily briefing of the top stories, we support 30 topics today and are adding the ability to add your own!

Stack is a combination of TypeScript (Next / Node) + Python with a pretty simple deployment setup right now (GHA -> Container -> Cloud Run).

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. That's why we created Upnext, our flagship product that lets users easily organize reading, audio, and video content in one neat space. We’re not stopping there, our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so Upnext users will always have the most important updates about topics they care about. We've got open roles for:

- Software developers: our tech stack is TypeScript / Node / React / Python - Designers: we're creating a seamless, beautiful experience across desktop, native and web - ML research / ML engineer: help us design build and deploy our first generation of recommendation and understanding systems - Marketing / growth: help us get the word out!

If you'd like to chat, email me at joe [at] upnext [dot] in!

Are there any similar open source tools that allow you to manage MacOS VMs? I'm aware of Lima / Colima but it seems they're for Linux only.

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML

At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. That's why we created Upnext, our flagship product that lets users easily organize reading, audio, and video content in one neat space. We’re not stopping there, our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so Upnext users will always have the most important updates about topics they care about. We've got open roles for:

- Software developers: our tech stack is TypeScript / Node / React / Python - Designers: we're creating a seamless, beautiful experience across desktop, native and web - ML research / ML engineer: help us design build and deploy our first generation of recommendation and understanding systems - Marketing / growth: help us get the word out!

If you'd like to chat, email me at joe [at] upnext [dot] in!

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML

At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. That's why we created Upnext, our flagship product that lets users easily organize reading, audio, and video content in one neat space. We’re not stopping there, our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so Upnext users will always have the most important updates about topics they care about. We've got open roles for:

- Software developers: our tech stack is TypeScript / Node / React / Python - Designers: we're creating a seamless, beautiful experience across desktop, native and web - ML research / ML engineer: help us design build and deploy our first generation of recommendation and understanding systems - Marketing / growth: help us get the word out!

If you'd like to chat, email me at joe [at] upnext [dot] in!

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML

At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. That's why we created Upnext, our flagship product that lets users easily organize reading, audio, and video content in one neat space. We’re not stopping there, our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so Upnext users will always have the most important updates about topics they care about. We've got open roles for:

- Software developers: our tech stack is TypeScript / Node / React / Python - Designers: we're creating a seamless, beautiful experience across desktop, native and web - ML research / ML engineer: help us design build and deploy our first generation of recommendation and understanding systems - Marketing / growth: help us get the word out!

If you'd like to chat, email me at joe [at] upnext [dot] in!

On a related note, are there promising models / techniques to detect these sort of instances?

Say for instance I summarize something and want to check that the result doesn't contain hallucinations (confabulations :)) or more specifically that the summary contains only information present in original text. What's current state of the art for something like this and how well does it perform? I've read some about entailment models and fine tuned LLMs for this sort of thing but haven't found many great resources.

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML

At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. That's why we created Upnext, our flagship product that lets users easily organize reading, audio, and video content in one neat space. We’re not stopping there, our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so Upnext users will always have the most important updates about topics they care about . We've got open roles for:

- Software developers: our tech stack is TypeScript / Node / React / React Native

- Designers: we're creating a seamless, beautiful experience across desktop, native and web

- ML research / ML engineer: help us design build and deploy our first generation of recommendation and understanding systems

- Marketing / growth: help us get the word out!

If you'd like to chat, email me at joe [at] upnext [dot] in!

Upnext | 100% Remote | Full Time / Contract | Software Eng / Design / ML

At Upnext, we are passionate about solving information overload. Every day we get bombarded with content from social networks, news sites, blogs, messages, etc. It’s hard to keep up and it’s even harder to find the content that really matters to you. It takes time and energy to sift through the noise and find what really matters. That's why we created Upnext, our flagship product that lets users easily organize reading, audio, and video content in one neat space. We’re not stopping there, our latest app helps you stay up to date on the topics and news that you care about by aggregating updates into a single place. Using our own AI models we’re building in deep personalization from the beginning so Upnext users will always have the most important updates about topics they care about . We've got open roles for:

- Software developers: our tech stack is TypeScript / Node / React / React Native

- Designers: we're creating a seamless, beautiful experience across desktop, native and web

- ML research / ML engineer: help us design build and deploy our first generation of recommendation and understanding systems

- Marketing / growth: help us get the word out!

If you'd like to chat, email me at joe [at] upnext [dot] in!

Anyone have good (preferably open source but not required) tools for running MacVMs on a Mac? Would love a way to programmatically control MacVMs (create new from image, start, stop, etc) as part of our Mac build server setup. GitHub actions Mac CI minutes are so expensive so we run our own setup and VM level isolation seems to be the best way to keep the build processes from stepping on each other.

By the way, I can also help you with more complex math problems, statistical analyses, or even help you learn new mathematical concepts. Do you need assistance with any other math-related inquiries?

Reminds me of my Amazon Echo and the reason I unplugged it :)

Are there models that can compete with gpt-3.5-turbo on cost per token at scale? From what I'm hearing the 30B+ models net out to a higher $/token but I haven't been able to find anything on the 7B and lower. Thinking about cost specifically here. We're exploring a couple fine tunes for specific tasks we have (we have the data to fine tune with) but gpt-3.5-turbo does reasonably well on the tasks so if the cost is an order of magnitude higher not sure the ROI is there.

In a non chat setting where the LLM is performing some reasoning or data extraction it allows you to get JSON directly from the model and stream it to the UI (updating the associated UI fields as new keys come in) while caching the response server side in the exact same JSON format. It’s really simplified our stream + cache setup!

Anyone know of any good “tolerant” JSON parsers? I’d love to be able to stream a JSON response down to the client and have it be able to parse the JSON as it goes and handle the formatting errors that we sometimes see.

Are there communities where one can go to learn more about fine tuning and running these things? I've found a bunch for diffusion models but haven't had any luck with LLMs.

I remember when they shut it down and I haven't found one that I've loved like Reader. Reader was beloved to the level of apps like Notion and Figma and nothing has come along to replace it in a way that works for today's content content landscape. A lot has changed in ten years, content has exploded in volume and decreased in average quality and every app started to feel as noisy as my social feeds.

Our users at Upnext (https://www.getupnext.com) are saying the same, so we're moving into the space with our next major release. Upnext 2.0 will allow you to follow anything on the web (Newsletters, sites, podcasts, YouTube channels, etc). If you're interested in trying out the beta you can sign up here: https://upnexthq.typeform.com/to/MYfd4pcK

In the meantime, I'd love to hear what folks are using today and why they miss Google Reader.