dimitrios1

it's "here is how to steal secrets on your way out" which is even grosser.

Thank you for recognizing this. As much as the developer community has come out against companies non-competes in the past, we should come down on even harder on one of our own stealing, because this does the most harm against the case against non-competes. It's grosser in the sense that one company doing a foul thing is bad, but ideally people can band together and work to dismantle the foul thing. But a person legitimizing the foul thing is the greater harm.

I have both as well. I trust the output of Claude to a higher degree than what I get with Codex. I always have claude review codex output. That being said, I find gpt 5.5 more generically useful at a wider breadth of tasks. Straight coding though, it's no contest.

Obligatory YMMV, maybe your prompting style fits gpt better. We forget that this matters a lot

I was excited for a second, because this is one piece of the puzzle (chords), then numerals solve melodies (you can just type something like 0-1 for open string first string, etc), then just need something for ornamentation. Seems like it only matches against a known set of chords, though.

I am glad! But you are indeed selling your own product here, correct?

This reads like a paid testimonial.

I know that these types of comments are not really popular here, but this struck a chord with me because I feel the same. They aren't remotely close.

I have codex right now purely because they gave me a month free of ChatGPT Pro, so I have been using it in between my usage resets with claude. Since it's "free money" for me I have been using it exclusively on xHigh.

One of my most frequent prompts is "hey codex worked on ____, but it didn't quite hit the mark, can we review the work..."

Yes, part of this is normal even within the same model -- you have the highest power model review the work for correctness, refactoring opportunities, and so on, but man I tell you, I don't know what it is about codex, this is obviously one guy's anecdote -- same prompting style, same repository documentation ala MD files, same skills, way different results.

All that to say, maybe the bug report is on to something here, and it can be fixed.

Don't be so negative nancy here!

I have been doing "modern web" things since essentially day zero (you kids with your fancy JIT compiled javascript interpreters!)

SvelteKit, and by extension, Vite, has been the single most productive webstack I have ever used. If this offers anything on top of that, I welcome it with open arms.

Far from being a meme!

My focus area in college was Computer Graphics. There is not enough focus about the math in this article, it just kind of passively mentions it. "Well you can get by with just a little bit of this and that" -- Linear Algebra is huge! So is an Engineering style Calculus course -- not your business calc. Those two require a year of their own to gain mastery. IMO, pick up:

Linear Alegbra Done Right Calculus Better Explained Concrete Mathmetics.

Then you can move on to the low level APIs.

I am another skilled senior, have been coding since I was 7, although you have a few more years of experience on me, and am commenting here just for the goldilocks moment, as I have read and reflected on both of your comments and find my reality is somewhere in the middle.

On personal projects, where I am in charge of all the hats (product development, UI, UX, backend, security, server admin, etc) -- absolutely crazy force multiplier. You get a nice suite of backend and e2e tests running, with full business scenario layered on top of that, and constantly running agents to do the coding, another agent on a higher level of reasoning to review that work, and sometimes occasionally poping into another competitors model to review their work just for added comfort -- it feels like wizardry. I am not vibing it, but I wouldn't say I am carefully scrolling through every line. I review whats fundamentally important, especially when it comes to data, overall structure, and large, cross cutting concerns, but I would be lying if I say some code doesn't land that I don't read. But I have the security of the test suites and validations , so I pour more effort into that.

It's a nice self reinforceing loop.

All of this might sound like I agree with you, and to some extent I do, but I am realizing as the apps I have built out like a cannon shot out of hell with tremendous speed and polish right out of the gate are starting to slow down. Feature adds are getting more complex. My memory is not what it used to be. Each run and pass through the code consumes more of my tokens and limits. I am starting to do less in the same amount of time. Codex did a vertical slice of a feature for me (well defined and well planned). It contained functionality that has historically plagued us developers -- the dreaded time. I used xHigh GPT 5.5. It had obvious bugs, but I wanted the robots to catch it. I popped it in claude (on the new sonnet 5! heyo!) -- Claude caught the bugs. Even said they "immediately stood out" I wondered how this happened. Frontier model from company A was evaluated by workhorse model from company B. All of this again took massive amounts of usage. And time.

And this is -- best case scenario, perfect world, everything is in perfect alignment.

Now for the work reality.

Multiple product and experience owners. Multiple dev teams. Different enterprise teams support services you rely on. You don't have full unfettered access to frontier models. You have to use copilot, or some other enterprise harness, and you run out of credits for the month, you are SOL. It's not as good as your claude, you think to yourself, but hey, its familiar enough, and you have 5k credits left for the month for Opus 4.8, better make the best of it. But now you burned half of them working on that Transactional Bug that was mixing synchronous and asynchronous semantics that the other guy's model should have picked up on. What happened? Maybe he didn't use Opus, maybe he used Haiku, maybe his prompt was bad. Who knows. Gotta fix it. Oh, you gotta reach across the isle and put in a request to get the Enterprise team to look at this caching inconsistency on user data that you need and is really the source of your race conditions. Tick tick tick. Model limits approaching. You start wondering if you just did all this by hand like "in the old days" would you have got it done correctly faster? Or at least, cheaper. You'll never know.

Yes.

I quoted something from deep in the article.

Did you read my entire comment, and assume the least bit of positive intent?

I acknowledged the main points the article brought up. I highlighted a glaring discrepancy, from my point of view.

When police act unjustly, hastily, or rash, in my country, it gets at least equal weight (typically more). We don't just focus entirely on the person or party who triggered the reaction.

Anyways, the reason I commented anything at all was, as someone who values true unbiased and objective journalism, something we need now more than ever, this is clearly falling short of their stated goals -- from their editorial policy:

"Doing journalism means taking responsibility for the public. We are aware of our biases and strive not for artificial objectivity but fairness."

Seems like a complete lack of awareness of the strong Anti-american bias, and a lack of taking responsibility for the Belgian public.

"Belgian police willingly comply with U.S. ambassador's request, and Belgian police stopped your reporting"

FTFY

a foreign ambassador had Belgian police remove us

Belgian police removed us.

FTFY again.

The article is making a good point, especially the hilarious irony of all the private companies, and US being complicit in limiting press freedom. But it also fails to recognize the agency and complicitness of the Belgian authorities as well, and makes them out to be some sort of innocent bystandards -- "Oh look those poor Belgians being bullied by the big bad US!" If they didn't want to remove you, they simply could have not.

I tried to run it on a M4 Air for shits and giggles.

After about 1 minute the entire machine basically bricked and I had to hard reset :D

I imagine your work machine, just like mine and everyone I've ever had, has application level limits to how much resources it can consume, spotify picks up on the limits, and adjusts accordingly?

As to what its doing with all those extra resources on your linux box... shrug maybe using your laptop to train its models or mine crypto?

"Hey Opus, migrate this site from jekyll to astro" doesn't work?

More than 50% of sets are now UB, and UB has been standard legal since ~mid 2025.

There's quite a few new cEDH staples from UB sets as well.

my favorite cEDH commander of recent memory is Aang at the Crossroads. Cast your commander, and roll the dice to see if you find the win.

and I would imagine close to 100% of the US 3d printing nerds that live there have the means to easily move to another state and continue their 3d printing nerdom.

There is a reason why California is leading the nation in migration out of the state.

The question I find myself asking very often these days: Is this better than asking claude to do the same things the plugin/repo does?

Not to be a contrarian, because I agree for a lot of the industry, but there are some genuine gems out there. Few examples:

Extreme Ownership really helped me be a better leader and take more accountability for my own actions

Atomic Habits really helped me think about goal setting and what the underlying driver was

Coaching Habit improved my 1:1s drastically (I basically stopped talking or advice giving and just listened -- profound, I know, but the book helped smack me in the face with it)

Many more examples, but there is definitely a ton of self-help hack slop out there as well.

I am against it for one reason only, but it's very solvable, IMO, and it's the amount of space they take up.

I live next to 200+ acres of solar farms. A part of me cries a little when I see so much beautiful land and trees cut down and these lifeless panels taking up so much space. We have so many buildings, and structures already (think parking decks, tops of apartments, homes, offices, even parking lots) that we could put these, but instead we cut down acres of trees or use up perfectly usable farmland.

I always viewed unions as a temporary solution to a long term problem. Fundamentally, its simply a unit or type of organization. But for some reason here in the west they have become this entrenched institution in of itself, presumably because it tasted a modicum of power, that power had real influence over people, and wherever there is an institution that exerts power over people, it becomes prime targets for demonic and corrupting influence.

You had guilds in the middle ages, and that worked well to serve the primarily agrarian feudal society. Unions worked well in a rapidly industrializing country with little to no enshrined worker protections or rights. We saw measured, direct, positive change. But the last 30 years or so, I can't really say the same has happened. In fact, some of the most unionized sectors have seen the most degradation. Blame who you will (I've heard it all in this point), but the main take away is its not working. Maybe its time for a new structure for this modern, post industrial society.

No other country relies on road travel to the extent of America, so I am not sure there is a good comparison to make.

So whats the solution? 37 people die every day in a crash involving an alcohol impaired driver. Do we think if we inhibit the police's ability to arrest drunk drivers, the world will be a better place? People are clearly not going to stop drinking and driving.

I am neither left nor right, but I feel like I need to say this much more in spaces that heavily lean left -- I wish we would focus on the actual crimes the police are there to stop as much as we do the police reform.

Ha! -- Allow me to introduce you to the US Diesel Truckin Nationals! Here are some dump trucks drag racing https://www.youtube.com/watch?v=aqxpOPeImkw

Even moreso . I like the Rob Pike restatement of this principle, it really makes it crystal clear:

"You can't tell where a program is going to spend its time. Bottlenecks occur in surprising places, so don't try to second guess and put in a speed hack until you've proven that's where the bottleneck is."

Moreso, in my personal experience, I've seen a few speed hacks cause incorrect behavior on more than one occasion.

If you were to take a positive intent approach:

- the warrant was for distribution of narcotics and kiddnapping.

If I were to guess what a list of most dangerous warrants to execute, those two would be up there.

If you note in the video, he jokingly plays around the drugs part. I am not sure where the kidnapping part comes from, but Afroman is not necessarily a household name amongst middle-aged white police officers, so I imagine they just saw "drugs and kidnapping" and went for it.

I distinctly remember from university in one of my more senior classes designing logic gates, chaining together ands, nands, ors, nors, xors, and then working our way up to numerical processors, ALUs, and eventually latches, RAM, and CPUs. The capstone was creating an assembly to control it all.

I remember how thinking how fun it was! I could see unfolded before me how there would be endless ways to configure, reconfigure, optimize, etc.

I know there are a few open source chip efforts, but wondering maybe now is the time to pull the community together and organize more intentionally around that. Maybe open source chipsets won't be as fast as their corporate counterparts, but I think we are definitely at an inflection point now in society where we would need this to maintain freedom.

If anyone is working in that area, I am very interested. I am very green, but still have the old textbooks I could dust off (just don't have the ole college provided mentor graphics -- or I guess siemens now -- design tool anymore).

I would wager that the vast majority of people commenting here about the pitfalls of AI, especially as it relates to governance and laws, are heavy users of AI, recognize the import and value it brings, and find ways to utilize it more themselves, so not sure using an ad-hominem dismissal of very valid objections are going to be effective.

(side bar: the phrase "anti-<whatever> luddites" is way, way overused, especially here. Let's get more creative, people!)

We live in different realities.

Opus and Sonnett practically writes the same idiomatic elixir (phoenix, mind you) code that I would have written myself, with few edits.

It's scary good.

will your retirement be enjoyable if everyone else around you is struggling?