kretaceous

To me, the article comes across as introspective (which by the way, I found extremely relatable) and not preachy.

Your comment also feels that you are not happy about where the industry is headed but don't you think your anger is misplaced?

In college (~5 years ago) I had to write a move-data-from-A-to-B pipeline¹ for a club. I had a simple version ready in ~1hour but it looked bad and slow. So I stayed up the whole night for the next 6 hours finding about weird MongoDB commands, discovering transactions from first principles², Node.js memory management. I commented it by hand and perfected the code. I don't know if I still have that code but it's a memory I often go back to.

I recently tried to write an elevator simulator (harder than I thought it would be) entirely on my own. I wrote the tests as a markdown spec and used an LLM to actually convert them to tests according to my interface. That was definitely a little gratifying, but not even close to what I used to feel. Of course, fully blaming LLMs is not really fair. There's also Life™ but LLMs definitely helped this soft-atrophy.

I simultaneously feel called out and encouraged by the post. The gym analogy feels apt. I guess I need to work on my recovery as well as hit a different gym which isn't named software.

1: I didn't know it was called ETL back then

2: I'm one of those weirdos who learnt a NoSQL DB first

One of the coolest things I've seen. I'd recommend the "Behind the scenes" video in the page.

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.

This was really encouraging to read for some reason, thanks!

A digital theremin! Very fun.

Can you give examples of how they are different? I've only done OOP in JS so I'm not aware of what I'm missing or what's supposed to be different.

Suppose there's the following situation:

    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.

Re: the lcm_expand(summaryID) tool

> 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?

Getting into reading again this year after a long break.

The most memorable read of this year was "The Count of Monte Cristo" (1846) by Alexander Dumas .

It's one of the greatest stories ever told. It's ~1250 pages but I sped through it in 3 weeks even if I'm a slow reader.

Highly recommended!

I also read The Stranger by Camus and the two top Orwells which lived up to the hype.