alexc05

Hey! This looks a lot like what I'm working on, from a slightly different angle. I think you're on the right track. In fact, cortex as a name is perfect since you're effectively building the executive function layer for search and selection. I also think rust is the right language to go with.

I'm going do a deeper read of your work in a bit. I'd love it if you took a look at my theory of artificial cognition The YAML of the Mind https://alexchesser.medium.com/the-yaml-of-the-mind-8a4f945a..., dropped in to the `ail` project and let me know what you think.

I just have to get the kids to school and I'll pop back into cortex later

Hey folks, I wrote this. If you're interested in the concepts or pressure testing the ideas a little deeper, please feel free to comment here or reach out directly.

I appreciate that it's pretty long feel free to point your LLMs at it

this is really exciting and dovetails really closely with the project I'm working on.

I'm writing a language spec for an LLM runner that has the ability to chain prompts and hooks into workflows.

https://github.com/AlexChesser/ail

I'm writing the tool as proof of the spec. Still very much a pre-alpha phase, but I do have a working POC in that I can specify a series of prompts in my YAML language and execute the chain of commands in a local agent.

One of the "key steps" that I plan on designing is specifically an invocation interceptor. My underlying theory is that we would take whatever random series of prose that our human minds come up with and pass it through a prompt refinement engine:

> Clean up the following prompt in order to convert the user's intent > into a structured prompt optimized for working with an LLM > Be sure to follow appropriate modern standards based on current > prompt engineering reasech. For example, limit the use of persona > assignment in order to reduce hallucinations. > If the user is asking for multiple actions, break the prompt > into appropriate steps (**etc...)

That interceptor would then forward the well structured intent-parsed prompt to the LLM. I could really see a step where we say "take the crap I just said and turn it into CodeSpeak"

What a fantastic tool. I'll definitely do a deep dive into this.

that's a bit of a meta discussion and it'd probably reveal some super interesting things about how tech culture have changed in the last ~15 years.

I've been on HN since 2010 (lost the password to my first account, alexc04) and I recall a time when it felt like every second article on the front-page was an bold directive pronouncement or something just aggressively certain of its own correctness.

Like "STOP USING BASH" or "JQUERY IS STUPID" - not in all caps of course but it created an unpleasant air and tone (IMO, again, this is like 16 years ago now so I may have memory degredation to some extent)

Things like donglegate got real traction here among the anti-woke crew. There have been times where the venn diagram of 4chan and hackernews felt like it had a lot more overlap. I've even bowed out of discussion for years at a time or developed an avoidance reaction to HN's toxic discussion culture.

IMO it has been a LOT better in more recent years, but I also don't dive as deep as I used to.

ANYWAYS - my point is I would be really interested to see a sentiment analysis of HN headlines over the years to try and map out cultural epochs of the community.

When has HN swayed more into the toxic and how has it swayed back and forth as a pendulum over time? (or even has it?)

I wonder what other people's perspective is of how the culture here has changed over time. I truly think it feels a lot more supportive than it used to.

> This isn’t a bubble inflating. It’s capital and intelligence relocating.

Is this GPT? this kind of not X but Y pattern is a real code smell for slop and can cause someone to immediately bounce out of your writing. The pattern can really feel hard hitting when you're reading what GPT put in front of you, but others are REALLY starting to reject it.

https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing

https://saigaddam.medium.com/it-isnt-just-x-it-s-y-54cb403d6...

https://www.blakestockton.com/dont-write-like-ai-1-101-negat...

Like it or not this can lead people to immediately reject your entire message, shut down and stop reading.

I agree completely and I don't think you can.

Even people recording short form video are doing it. They're reading out their chat-gpt-psychosis induced fever dreams using scripts written by chatGPT.

The 7-part tweets that build to a slop crescendo are doing my head in.

The solution might be some combination of:

1. leave the social media sites where the slop is irredeemable. 2. unfollow everyone, reset your algorithm. 3. be aggressive about who you add back in. Make sure they're humans having high quality discussions. 4. be aggressive about who you block. Lower the bar on blocking - one and done. No chances, no wait-and-see. 5. move to smaller communities of real humans.

None of this has worked for me yet. I'm still swimming in a vast sea of slopity slop slop. Dead internet theory appears to be playing out in front of us.

edit: On threads I've been trying to use their `dear algo` feature pretty aggressively but it doesn't work very well. I've asked it to remove some types of comments and it seems to just add more of them.

If I could have one of these cards in my own computer do you think it would be possible to replace claude code?

1. Assume It's running a better model, even a dedicated coding model. High scoring but obviously not opus 4.5 2. Instead of the standard send-receive paradigm we set up a pipeline of agents, each of whom parses the output of the previous.

At 17k/tps running locally, you could effectively spin up tasks like "you are an agent who adds semicolons to the end of the line in javascript", with some sort of dedicated software in the style of claude code you could load an array of 20 agents each with a role to play in improving outpus.

take user input and gather context from codebase -> rewrite what you think the human asked you in the form of an LLM-optimized instructional prompt -> examine the prompt for uncertainties and gaps in your understanding or ability to execute -> <assume more steps as relevant> -> execute the work

Could you effectively set up something that is configurable to the individual developer - a folder of system prompts that every request loops through?

Do you really need the best model if you can pass your responses through a medium tier model that engages in rapid self improvement 30 times in a row before your claude server has returned its first shot response?

According to google Tesla has shipped 8 million cars total since inception. It is valued at 1.32 Trillion as of today. Which is roughly $165,000 per shipped vehicle.

Right, let's not forget that he's selling it to himself in an all stock deal. He could have priced it at eleventy kajillion dollars and it would have had the same meaning.

He's basically trading two cypto coins with himself and sending out a press release.

it seems like our software engineers included `censorship=true` in the latest build when someone filed a JIRA ticket that said "censor stuff"

we're going to class this one as low priority / won't fix.

can you post the correct link in the comments?

this appears to be a redirect away from static assets.

looks like you've got to go here or their systems will mess you around: https://www.goldmansachs.com/insights/top-of-mind/gen-ai-too...

do it on mars then... that would have the added benefit of heating the planet so we could live on it. It seems so obvious if you think about it. Someone transfer eleventy trillion dollars to Elon Musk so we can get started.

the 4hww was such a damaging read for me. I wasted YEARS squeaking pennies out of shitty, poorly-realized side hustles trying to solo that shit when the real ROI would have been to focus on leetcode in my 20's and track down a role paying 10x the salary.

When I first read it, I was probably making about $60-65k and scrambling for $2.5k raises with a shitty meat-grinder employer while burning the midnight oil and acting as a "weekend warrior" trying to come up with something that would allow me the freedom that ferris spoke of.

Problem is, all of his techniques presumed you already had some sort of business that you could automate yourself out of.

If you're a wage-earner none of the shit he talks about is realistic. Sure, you can do the research to become a drop shipper or to place tiny ads in the back of soldier-of-fortune for brain pills.

For the typical computer programmer - your ROI will be 100x higher if you just get good enough at algorithms and system design to land a role at a company with Tier3 compensation.

when people do these complex CPU designs in minecraft are they laying the blocks individually in real time and in 3d space - or are they scripting some sort of algorithm that instantiates the system in one go?

It's impressive either way but the manual version seems ... impossible.

What an oddly editorialized version of this headline which does not appear to reflect the conclusion made by the article OR the actual headline of the linked article:

actual headline:

> Is Marvel leaving Georgia? Production shifts to UK spark industry shakeup

piece talking about reasons:

> shifting to the United Kingdom, where lower production costs, especially on wages and employee benefits, are giving studios more bang for their buck, according to the Daily Mail.

looks like differences in wages AND benefits. Lower overall salaries in the UK combined with public healthcare costs via the NHS is a much more nuanced take than "leaving to avoid paying health insurance."

I suppose the conclusion though is the same - that a public option would have prevented this flight of capital. Not necessarily dropping of mandates that employers cover health insurance to remain competitive (which I'm sure some will conclude).

I'd argue that Meta's income derives in no small part from their best in class ad targeting.

Being on the forefront of

(1) creating a personalized, per user data profile for ad-targeting is very much their core business. An LLM can do a very good job of synthesizing all the data they have on someone to try predicting things people will be interested in.

(2) by offering a free "ask me anything" service from meta.ai which is tied directly to their real-world human user account. They gather an even more robust user profile.

This isn't in-my-opinion simply throwing billions at a problem willy nilly. Figuring out how to apply this to their vast reams of existing customer data economically is going to directly impact their bottom line.

100% yes! There've been some other writers who've been doing parallel work around that in the last couple weeks.

https://www.dbreunig.com/2025/06/10/let-the-model-write-the-... is an example.

You can see the hands on results in this hugging face branch I was messing around in:

here is where I tell the LLM to generate prompts for me based on research so far

https://github.com/AlexChesser/transformers/blob/personal/vi...

here is the prompts that produced:

https://github.com/AlexChesser/transformers/tree/personal/vi...

and here is the result of those prompts:

https://github.com/AlexChesser/transformers/tree/personal/vi.... (also look at the diagram folders etc..)

thank you so much!!

Because medium is such a squirrely interface I find myself writing in markdown in vscode then copying and pasting sections across. If I make an edit after I've stared inserting images and embedding the gists it gets a bit manual.

Your comment in addition to another one about finding a way to compare the outputs of the good/bad prompts side by side - 100% agree. This could be more robust.

While I am running a process transformation against production teams in small isolated experimental groups, I can say I'm getting really great feedback so far.

Both with the proprietary stuff happening in the job, and with the feedback I'm getting back from the engineers I've shared this with in the wider industry.

Feedback from colleages who have started taking "selected pieces" from the "vibe engineering" flow (https://alexchesser.medium.com/vibe-engineering-a-field-manu...) has been really positive.

> @Alex Chesser i've started using some of your approach, in particular having the agent write out a plan of stacked diffs, and then having separate processes to actually write the diffs, and it's a marked improvement to my workflow. Usually the agent gets wonky after the context window fills up, and having the written plan of self contained diffs helps a lot with 'checkpoints' so I can just restart at any time! Thanks!

from someone else:

> I just went through your first two prompts and I'm blown away. I haven't done much vibe coding yet as I've gotten initial poor results and don't trust the agent to do what I want. But the output for the architecture and the prompts are mind blowing. This tutorial is giving me the confidence to experiment more.

benchmarking feedback vs. qualitative devex feedback is definitely a thing though.

editor's note: title also chosen for the clicks.

I don't know, I thought it was a fair question :shrug: :)

I'll admit that it's a little shoehorned in at the end :)

... but you know how editors are with writing the headline for clicks against the wishes of the journalist writing the article. You'll always see Journos sayign stuff like "don't blame me, that's my editor, I don't write the headlines"

I did toy with the idea of going with something like: `Prompt Engineering is a wrapper around Attention.`

But my editor overruled me *FOR THE CLICKS!!!*

Full disclosure: I'm also the editor

I can't republish anything that happens in a production/proprietary environment.

One of the things that I think is pretty great about being able to share these particular prompts is that you can run this on one of your own repos to see how it turns out.

ACTUALLY!! Hold on. A couple weekends ago I spent some time doing some underlying research with huggingface/transformers and I have it on a branch.

https://github.com/AlexChesser/transformers/tree/personal/vi...

You can look at the results of an architectural research prompt.

Unfortunately I don't have a "good mode" side by side with a "bad mode" at the moment. I can work on that in the future.

The underlying research linked has the experimental design version of this with each piece evaluated in isolation.

Hey Folks! Alex here :)

I appreciate that this is long. You may have hopped on with your morning coffee, hoping to take in a few memes and hot takes before getting to work for the day. Then this monstrosity shows up.

Based on my beta readers' feedback of "too long" I've added things like a 2 minute summary at the top to try and let you know what you're in for, and a table of contents (sadly not working. it will when I republish on github) to hopefully let you skip to the bit that you're interested in.

You definitely don't have to read it all, especially as a front-line engineer but the leadership justification part is in there based on the pushback and "pressure testing" I've seen from people up and down the org chart.

As much as this IMO is an incremental shift in direction that should fit within a "normal" modified agile/scrum workflow, If you think about the cost of hopping onto a new workflow there's risk.

We're talking about an expensive bet here. Realistically your teams aren't going to know that this works for a quarter to a half. A long term shift in the way you do things takes time to sink in.

Costing out that bet on a team of 4 engineers an EM, PM and, Designer we're looking at say $20k/week/employee or between $2 and $4 million. You can fiddle the numbers around here since they're likely not going to get _nothing_ done but you get the idea.

Scale that to an organization and ... well it's a lot.

If leadership is going to allow you to adopt a whole new way of doing things, you're going to need a lot more rigour than just "trust me bro"

The size of the article in that respect is a feature, not a bug.

Leaders can hop off the train when they're satisfied that it's worth a try. The engineers can jump to the "just tell me what we're doing" bit.

I hope you read it all, have a robust discussion and really pressure test the ideas so I can refine the process. I'll take your accolades and your angry criticisms with equal excitement

(please be nice though, I really did try hard here).

Feel free to reach out directly!

open router doesn't have that really slick graph though :)

Wait - does everyone here think they're talking about AI? Or is it bitcoin / crypto / NFTs?

As much as I appreciate the sentiment, it is starting to look like bad things happen to OTHER people when the extremely powerful get disconnected from reality. I feel like Marc Andreessen falls into the "bad things will happen to other people" category here.

the mouseover tile expansion is way too big. if I like to hover my mouse over the thing I'm looking at as I scan the display, the expansion is so big that I can't see the next item to the right making the list painfully un-scannable for a certain UX.

don't zoom the tile. feel free to color-swap, display condition, whatever just don't mess with the size ESPECIALLY not a 200% zoom.

also - super buggy if I mess with the filters a little. looks like you're somehow registering "discounted item price" as "%savings" and reporting a $935.55 item as "93600% savings"

keep going though :) just a few kinks.