bilater

I'm curious for ppl who grew up in the US: did you have to use pencils or fountain pens with ink in class (this was the norm for me)? At some point we all switched to ball point pens which was a lot more convenient but not as much fun.

I sort of believed this but also 4.5 coming out last year would absolutely have been a big deal compared to what was out there at the time? I just dont understand why they would not launch it then.

Nice - I like people's different twist on Deep Research. Here is mine...with Flow I'm trying a new workflow.

https://github.com/btahir/open-deep-research

My weekend project Open Deep Research got more traction than I would have thought.

https://github.com/btahir/open-deep-research

An open source alternative to Gemini/OpenAI deep research. I'm experimenting with this cool flow chart workflow that I think can be a cool twist on generating reports for deep research.

Check it out and lemme know what you think. :)

Agreed. I think its something to look into but surely the boomers who went through the plastic industry in the 60s had it way worse when we had way less stringent standards and were getting exposed to and even eating now banned substances. If they survived it..and by survive I mean lived to a healthy 80-100 year life for the most part then we probably will be fine.

This is precisely why I have said that every new framework/library should have a markdown or text or whatever is the best format for LLM models endpoint that has all the docs and examples in one single page so you can easily copy it over to a models context. You want to make it as easy as possible for LLMs to be aware of how your software works. The fancy nested navigation guide walkthrough thing is cool for users but not optimized for this flow.

dude is living his best life. and its an open question whether you need to be damaged to be worth that amount of money.

It's rare I come across something so myopic, unimaginative and laughable. This will age as well as the Paul Krugman prediction:"the Internet's impact on the economy has been no greater than the fax machine's". We have not even begun to explore the Uber/Airbnb applications of a 6G+ world. And the VR bandwidth ceiling lazy thought is an extension of the limited mindset of this author.

I think the way to swallow this bitter pill is to acknowledge they can "generalize" because all human knowledge is actually a relatively "small" finite distribution that models are now big enough to pattern match on.

Not quite the agent they are building but I have an open source alternative that lets you use a variety of models, based on links of your choice to generate reports: https://github.com/btahir/open-deep-research

Great video covering the API: https://youtu.be/oOK3UzLJ_Cs?si=1MJYtFBmcyJs4tLj

I like the batteries included option and would likely use it a lot. But not sure why they simply did not make a "batteries" package you could install on top of core and avoid the inevitable push back they knew they would get from this.

Nice I was thinking about launching an API because providers like Replicate have long queues. I think if you can nail down latency and concurrency you may get a lot of users who need reliable fast TTS.

The sad game theory result of this is that no one ends up caring or comes to the conclusion there is no point of caring. Wonder if it is at all possible to reverse it once you fall in this cycle.

what a bizarre take - the premise of controlling your universe and presumably your self is you can do whatever. If you would rather be a peasant in the 13th century then you can simulate that too. and perhaps, you're already doing it.

That is the end game - your own little miniverse with you as the central character. And I think thats awesome.

Here's my book journey as a visual :) https://x.com/deepwhitman/status/1872821464417878256

This is easy to say but the reality is being a monkey and throwing money in the market over the last 15 years would have made you f u money. Yet most people never did it. So who is the genius: the guy who remains on the sidelines and eventually is proved right or the guy who remained in the market and did face a brutal correction. One thing I've learned about myself is that I'll never be the guy on the right end of that mid curve meme so I might as well lean in on being on the left.

I created a simple tool to play with the optimal bet size on v0. Interesting.

https://v0.dev/chat/1u6efMupysC?b=b_sxkDz7R6crr&p=0

Nice - I can see some cool agentic flows created using this. A thing I want to look into is creating a sandbox instance (Ubuntu?) and letting an agent do its thing. Could be collecting data or answering questions and I can pull up the window to check in from time to time. It'll be like having an assistant.

Disappointed in this article. I was hoping to get some introduction to Beers methods especially compared to naive centralized planning but its mostly about how Beer didnt live up to his potential.

Again - think of where we were two years ago. I never understand this hubris people have to think AI can never do X while being proved repeatedly wrong.

bumped it up

I have more than 50 projects and find myself often bogged down by fixes and updates. This can creep up on you. Going back to older code bases (even ones you wrote) can be daunting and annoying. One customer email can ruin the whole day. AI has definitely made this easier but it's still challenging.

I've now started to be more ruthless in cutting older projects that aren't going anywhere (or are not 100% automated) and I also try and consolidate new project ideas as a features to existing products.

Still its hard and everything is a balance. Some of my projects in case anyone's interested: https://www.hackyexperiments.com

ohhh

Who uses gnome? Why would you use Gnome over other linux distros? I'm not asking as a diss I genuinely don't know much about the different preferences ppl have for open source OS.

" People who are saying React only belongs on DOM are missing out"

yup - two of my favorite React packages are Remotion and React Email.

Currently focusing on making my main app the best YouTube productivity tool ever.

https://www.you-tldr.com

It initially was a simple youtube transcript + summarizer but I've added a bunch of more features. My goal is to make it the tool that lets a user go from video to insight in the shortest amount of time.

Would love any feedback and ideas around this!

Recently did a standup comedy app where an AI laughs at my jokes: https://github.com/btahir/standup-comedy

I really wish there. was a two line answer to these long drawn our articles