My comment is more or less "I get the problems and I am not seeing the market agree that there even is a problem". It's capitalism manifest: squeeze the workers as hard as you can, get the next batch when the current one gets drained. Those incentives always existed and AI amplified them, that's all there is to it really.
Maybe the article is introspective, sure, but I am beyond the phase of realizing those kinds of problems and so to me it reads like meaningless repetition and merits only a sarcastic "Oh really? Never would have guessed." eyebrow-assisted remark from me.
I get it that's not a popular point of view -- HN really loves their virtue signalling and the ever-present "we must do something!"... whoever "we" is, that's never specified, naturally. But I am not karma farming, so people can and should freely cast their votes on my posted comments.
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
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.
which reminds me of building breadboard RF sensors (using fixed caps with variable for calibrating parasitic capacitance) and since these are just oscillators you can calibrate a beat frequency (heterodyne mix) in audible range that has the theremin timbre of a squarish sine wave that you can plug straight to a speaker
> 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?
By construction, individual summaries are not typically large enough to overload the context window when expanded.
The reason that the volume is potentially arbitrarily large is that one sub-agent can call lcm_expand multiple times - either vertically or horizontally. But that's a process that occurs gradually as the tool is used repeatedly.
This has not been a problem in our testing, but if it were a problem it would be easy to prevent sub-agents from invoking lcm_expand once their context buffer has reached a specified threshold.
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.
Another question is, why would earlier conversations need to be stored and recalled? They're irrelevant. Only records of the initial requirements and the work done, or work in progress, needs to be stored.
You could definitely build a coding agent that way, and it sounds like you've done it. We store the conversation history because:
1. In our use of coding agents, we find that there are often things referenced earlier in the conversation (API keys, endpoint addresses, feedback to the agent, etc.) that it's useful to have persist.
2. This is a general-purpose LLM memory system, which we've just used here to build a coding agent. But it is also designed for personal assistants, legal LLMs, etc.
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.
Thank you. I believe this is because it's not properly aggregating the story title, content, and comment hierarchy. There are going to be cases where the LLM does a poor job of understanding the conversation, but I think right now the information isn't being sent to the prompt.
Right now it seems to be only using one level of the parent comment hierarchy.
The Count of Monte Cristo was published in serial form. Daily from 1844 to 1846.
That explains a lot the format, which tended to try to retain the audience.
Also, the author wrote in advance of the daily publication, but the book was written "live", answering to public perception and response. This is a reason why the book is so "good": the author had the chance to adjust the story based on data from sales and feedback from readers.
Of course Dumas was a great writer too, but this live writing, data based is probably why the book resonates so well with audiences.
So, as a joke, if you read count of monte cristo in 3 weeks, you did the equivalent of bing reading it.
This happens with soap operas too. 10 years ago, they lasted 1 year. They had an initial structure, the story, the characters, but responded in "real-time" to audience feedback.
For those willing to read the book, give yourself some time. Try to read it over a course of some years. Read a little, come back to it.
There are several famous books written in the same form, like Crime and Punishment or The Three Musketeers.
Oh, and also authors got payed by installment, so that explains the lenght lol
Loved the stranger, I read it for the first time this year too. I read plenty of sub culture (mostly modern; Irvine welsh etc) but the stranger was just so different than anything I’ve ever read. Like the language is so olan yet it works so well, and then you have this great finish, it’s a weird masterpiece.
Your comment also feels that you are not happy about where the industry is headed but don't you think your anger is misplaced?