Here he mentions "Store trajectories " is a tent pole to see vectors of work over time which goes back to the point above. But also, will that trajectory be stored in the agent/framweork, or will it also need live elsewhere for us humans?
like with most agentic dev I do these days, I go between "I need this" to "I used to need this when humans were involved but is it just vestigial" a lot. In this case, why am I documenting at all if the agent is pretty good at understanding things quickly via the context and indexes it creates from the code itself.
...on the other hand... since we still have humans using the features and interacting with them, knowing what is going on and why it made a decisions (for better or worst) doesn't seem like something to let go of.
What a cool concept to turn the SM 140 chars concept into a programming demo list! Is there a reverse to this that work to compress a JS script into 140 chars to help show some creative ideas without needing to fully understand the code? Also, how good is AI at generating these in your experiences?
A friend of mine is using N8N a lot, but he isn't a developer and I think that is the main reason. I think LangChain is the most popular, but there is always a trade off between upstart costs, and the cost of forcing a pre-fab to fit your needs as you grow. I personally have used NextJS's AI SDK a a lot since it is very web friendly (nodejs/JS) https://ai-sdk.dev/docs/introduction.
Interesting. I use a lot of python and nodejs for my apps, maybe this shell angle is a weird quirk I developed for no particular reason. I keep a seperate repo called “manager” and use it to manage my other parts of the stack like, “run tests for each repo, bump version, commit to git” with a single CLI command. I have no idea why that started. My guess is an agent created a shell script and I just went with it and built up around it. Good to hear other perspectives. Thanks!
There is a reshaping of what we think is “right”. Like, I am less and less interested in SDKs since I can just ask for a lightweight, custom, integration into anything I want based on API docs. I mean, I still use a lot of SDKs…buuuut it feels like I’m forcing the AI to use them for my monkey brain’s sake. Is predefined mashup of structured services even necessary anymore?
Dude - crazy. When I saw this post I was like - finally someone said it. But it isn't just "iPhone". Why is spell check so bad EVERYWHERE..... still?. Like, how is it I am still even able to share texts, emails, etc that have mistakes at all? I feel like "spell check" is so old school. Intent, and matching intent, without typos is way over due. A bit meta: but, I am going to have to re-read this post - why? I still send texts that say "What re you doing?" - hwy?
Finance people are funny. They are so wrong when you hear their logic and references, but I also realized it doesn't matter. It is trends they try to predict, fuzzy directional signals, not facts of the moment.
What you make of this memo really depends on who you are and how you're positioned.
The dot-com era was absolutely a bubble. Tons of companies died, but the internet itself didn't go away, and the people who backed the right companies did extremely well. The 2007 housing bubble, on the other hand, was a totally different kind of event: broad, systemic, long lasting, and painful for almost everyone.
AI looks a lot more like the former. Some companies will fail, valuations will swing, but the underlying technology isn't going anywhere. In fact, many of the AI firms that will end up mattering are probably still undervalued because we're early in what will likely be another decade long technology expansion.
If you're managing a portfolio that needs quick returns and can't tolerate a correction, then sure, it probably feels like a bubble, because at some point people will take profits and the market will reset.
But if you're an entrepreneur or a long-term builder, that framing is almost irrelevant. This is where the next wave of value gets created. It's never smooth and it's never easy, but the long-term opportunity is enormous.
I feel like it allows me do more of the fun bits of coding and creating. It's not too different than giving the easy/basic/annoying stuff to consultants and less senior engineers. Do people get mad when the hire more devs? You still get to machinate over how to attack a problem in clever ways. Also, you can give 4 out of 5 tasks to the AI and leave the fun bits for yourself.
This is perfect for AI video creation. Everyone is dead so you can easily get likeness for the actors and produce a teaser real for pennies on the dollar. Did you try that yet? Throwing that on a post and/or youtube will get a nice ghetto test of interest you can then show some execs - 1M views is the new "here is my idea".
How he created a world around his CV may not be groundbreaking, but very creative and done exceptionally well. I caught myself driving around for a couple minutes. Accepting cookies bakes a cookie, you get hidden easter eggs when you complete certain actions (like lift driving in water). Just like with any creative endeavor (movies, music, dance) doing something no one has ever seen isn't always the goal (striving for that can often feel forced/cringe); creating an emotion in someone is art - and this did that for me.
Don't they have to cache in order to access the tools quickly enough to run the agents? I imagine not doing slow would slow down the progress considerably. Or, maybe I misunderstand which part of the flow/agent/work you mean by "cache on tools"
Loved Oliver Sacks. He was such a kid at heart with a big brain and soft demeanor. His interviews are great. Here is one https://www.youtube.com/watch?v=4AnuxDdg2II It is rare a lisp can improve how one sounds, but I like his.
Takes a min to load even when it shows the circle complete. But a 1-2xrefreshes load it and yes, it is pretty sick. Wish you could zoom out more though. Nice work to Bruno!
My gut reaction is, if AI was really good at vibe coding all the infra it could be nice, but getting C deployed and productized is the potential challenge. The "roads" we built for hyper scaling apps doesn't strike me as C friendly. And, even with the friendlier deployment strateies on next, python, etc, AI still slips up a lot.
haha - yah. From a pure marketing perspective - vapor ware is here 100%. I'm pretty sure we are all supposed to be in self driving cars by the end of this year.
https://x.com/Khaliqgant/status/2019124627860050109
Here he mentions "Store trajectories " is a tent pole to see vectors of work over time which goes back to the point above. But also, will that trajectory be stored in the agent/framweork, or will it also need live elsewhere for us humans?