leonflexo

I think Bun helps with the memory pressure, granted this is relative to V8. I'd pushback on the certainty with the reality that TS provides a significant drop in entropy while benefiting from what is a sweet spot between massive corpus size and low barrier for typical problem/use-case complexity. You'll never have the fastest product with JS, but you will always have good speed to market and be able to move quickly.

Bun uses JSC (JavaScriptCore) instead of V8. From what I understand, whereas Node/V8 has a higher tier 4 "top speed", JSC is more optimized for memory and is faster to tier up early/less overhead. Good for serverless. Great for agents -> Anthropic purchase.

I wonder how much of a lost in the middle effect there is and if there could be or are tools that specifically differentiate optimizing post compaction "seeding". One problem I've run into with open spec is after a compaction, or kicking off a new session, it is easy to start out already ~50k tokens in and I assume somewhat more vulnerable to lost in the middle type effects before any actual coding may have taken place.

The tech/demand for the glasses didn't break through some threshold it hadn't reached before, all of the sudden. They became viable as a product again because real training data is more valuable now than ever.

If the answer is, "of course not". Pull that thread. Honestly, so much "therapy" for some of us boils down to confronting/examining that disconnect and exploring why it exists/how it came to be.

> Chinese operators allegedly disguised themselves as US immigration officials

What's that, a little speaker?

How far the volatility ripples out will give us a real look into just how self-reinforced the financials truly are.

Similar to how we are seeing LLMs shoved into spaces where existing ML was already doing well and better suited.

Not to dismiss the value of LLMs in those cases as an interface/interpretation layer.

If grandma goes into the windowless surgery factory, I just want the best bots working on her. There is value in having Dr. Bot the replicant give me the face-to-face status updates. We are not breaking out those layers as much, anymore, as the focus becomes minimizing FOMO.

Systemic inefficiencies aside. I wonder how much of that is a public funding feedback loop? The cost gets higher, because the standards, requirements, and processes are stricter, because there is the need to validate the use of public funds, exacerbated by being higher, increasing the standards/requirements etc etc... Especially in a political environment where there is no shortage of sniping funding for points.

Regardless, first thing it reminded me of was that interview quote about how if nasa had SpaceX track record they would have lost funding long ago. Is there a US political landscape, even back to 2008-2016, where that isn't the case?

Great show and fantastic music. This show and Driver were two soundtracks that captured that early/mid 2010s vibe for me personally.

> Its also worth noting that if you can create a business with an LLM, so can everyone else. And sadly everyone has the same ideas

Yeah, people are going to have to come to terms with the "idea" equivalent of "there are no unique experiences". We're already seeing the bulk move toward the meta SaaS (Shovels as a Service).

"We’ll always offer a way to not see ads in ChatGPT, including a paid tier that’s ad-free." Plus will be next.

I thought hypertrophic focused routines were their own subset. Starting with a high rep, like 20, decreasing something like 2/week while increasing the weight. You technically can increase load, but in my experience it isn't strictly necessary. 10-12 weeks down to 1-2 reps then 3-4 off to reset. This isn't a strength routine, simply for size relative to lift.

I only read this because while messing around with learning some basic VPS and NGINX, I used Claude to spin up some quick frontends. One ended up being a geocities hackernews clone. Then while getting some basic process and terminal experience, I piped into Codex CLI to generate a summary modal to my visual liking. All of that to say that while I could have done it on my own, I likely wouldn't have because it allowed me a low friction path to implementing the bits that weren't crucial for what I was trying to learn.