This is relatable. I find myself using LLMs more in cases where I don't care about learning and have made multiple tools to fir my workflow (Swift apps, etc. without ever touching Swift code). When it comes to things I do know about or want to learn about, I'm avoidant towards them because I know I can do better even if slower; but the procrastination for these has definitely turned into disinterest.
Summary A = summarise(message 1 to P)
Summary B = summarise(Summary A, message P+1 to Q)
Summary C = summarise(Summary B, message Q+1 to R)
What does calling lcm_expand(Summary C) do? Does it unroll all messages from message 1 to message R or does it unroll to Summary B and message Q+1 to R?
> volume is potentially arbitrarily large is that one sub-agent can call lcm_expand multiple times - either vertically or horizontally
I'm assuming from this that it's the latter? In that case, that addresses my concern about not blowing up the context window immediately.
> Because expansion can recover arbitrarily large volumes of earlier conversation, this tool is restricted to sub-agents spawned via the Task tool; the main agent cannot call it directly. This restriction prevents uncontrolled context growth in the primary interaction loop.
What if the lcm_expand is called for a summary that has 1000s of messages that immediately floods the sub-agent's own context window?
Does lcm_expand only unroll one "layer" of the DAG and unrolls more if needed by another subagent?
This is really cool and something I've envisioned building for a long time!
There is a bug in the entity tracking. For the entity "github", it shows a positive sentiment. HN does NOT like GitHub (for reasons good or bad). If you click on it, it shows you stories about other seemingly unrelated stories.
I'm confused by what Cursor is trying to be. They shipped plan mode and debug mode which are developer focused tools and I'm happy about them.
On the other hand, features like these are kinda distracting to me. I wouldn't mind if it wasn't for the core product and developer features getting buggier day by day.
I've been facing a number of rough edges lately. The plan mode's support for multiple plans in a single chat breaks often, todos don't get created or marked properly, the new changed files UX is atrocious (just take me to the file), it's not able to adhere to simple prompts in a low context window usage chat (Sonnet 4.5), etc.
It sucks to try different editors every few months but I might have to do that if this continues.
> We’ve seen 2x speed improvements in type checking times for internal projects when using TSGO.
That's a lot less that what TSGO promised when it was first announced (A 10x faster Typescript¹). Hopefully this is just the result of it being experimental.
- Smallest animal: Myxobolus Shekel. Smaller than a WBC at 10 micrometeres.
- Biggest butterfly: Queen Alexandra's Birdwing. Bigger than human brain at 18cm.
- Largest insect to ever live: Meganeura (283 MYA). At 40cm long, a dragonfly larger than a house cat.
- Rafflesias are larger than German Shepherds
- Earth's largest crab: Japanese Spider Crab. 1m, legs pan of 3.75m. More than half the size of a human.
- Always thought Mososaurs were largest animal to ever live but it's the Blue whale at 26m. I don't think I ever appreciated how unfathomably huge they are. (The largest Mosasaur found was 13m. There's a speculated size of 17m as well.)
- World's largest living tree: Hyperion - a giant redwood in california at 115m.
Love seeing something so polished and inspiring. Amazing illustrations and even better music.
A linter rule provided by the library could be helpful here. I know it's just a workaround but probably easier than going for a solution that does compile time checks.
I attempted something like this because I wanted a good books search service which provided me at-a-glance information I needed from Storygraph & Goodreads. The main things I look for when I search a book is genres/Storygraph's "moods", number of pages, whether it's part of a series, rating across services & how much does it cost.
The first two sections reminded me of an observation I've made about myself: the more I delay "doing the thing" and spend time "researching" or "developing taste", the more I turn into a critic instead of a creator.
> Your taste develops faster than your skill
> "the quality group could tell you why a photograph was excellent"
They are critics now. People with a huge taste-skill gap are basically critics — first towards themselves and gradually towards others. I don't want to generalize by saying "critics are just failed creators", but I've certainly found it true for myself. Trying to undo this change in me and this article kind of said all the words I wanted to hear. :)
It's both dense and beautifully written. Feels like every paragraph has something profound to say. This kind of "optimizing-for-screenshot-shares" writing usually gets overdone, but since this actually had substance, it was amazing to read.
If the Uranium came from multiple supernovae, then why is it shocking that earth has different concentrations of U235? Moreover, how is it proof of a past fission reaction?
What if that "part" of U235 came from a separate supernova which is a little older and some more of its U235 had already decayed?
These are two very different things here, I think. You're talking about celebrity and franchise fandom which is parasocial and exists because they are actively influencing you to become their fan. They're already famous or have made it.
What the article talks about is much more grounded – being excited about other people you know and believing in them. This "fandom" doesn't necessarily originate from admiration of achievements but from sincere belief. You're becoming a fan while they're just being themselves.
This was comforting because I have these constant worries but I think it's a false comfort.
> Your brain is telling you something important—listen to it
I don't trust it cause it's often wrong and sucks at prioritising. Sometimes, the stimulation an ADHD brain is looking for can be in form of something actively detrimental. If I "listen to my brain" in the moment, there's a significant chance I don't come out stress-free at the end of the day and instead become more anxious.
I'm all for increasing things in your life that you want to do more of. But that often takes doing things instead of giving in.