dkdcio

fair enough! the jump from that to ChatGPT’s launch (which I didn’t find that interesting), to gpt-4, to Claude Code/Codex CLI, to Gemini 3/Opus 4.5/GPT 5.2 has been insane in such a short time. I’m excited (since the release of the Codex CLI especially: https://dkdc.dev/posts/modern-agentic-software-engineering/)

technical preview in June 2021. I was using it for a bit before that as an internal employee. so they may have rounded up slightly or also were an internal beta test

side note, I’ve been trying to remember when it launched internally if anybody knows. I feel like it was pre-COVID, but that’s a long timeline from internal use to public preview

> Imagine the ad police. “You blogged about a product. Someone said you sounded insincere. Let’s see the receipt for purchase. Can’t prove you bought it? Prove you weren’t compensated for your blog post or pay a fine.” Kafka land.

immediately to a fantasy slippery slope argument, cool!

your argument seems to boil down to paid ads being the lifeblood of the flow of information. my argument is it corrupts that flow of information, and we’d be better without them —- everything would operate just fine. individuals and organizations would have better incentives to share valuable information, not what they get paid to. obviously there would be plenty of details and edge cases to work out, as with any policy in the real world

I’m not going to write out policy in HackerNews comments and play that game with someone who jumps to the “imagine this crazy world where the police start arresting all of us over free speech!” as their explanation for what would go wrong

and you can switch AI providers, or use local LLMs. again, a nonsense point to raise about how FOSS is developed. coding “by hand” also doesn’t go away. if you lose your proprietary tools (laptop, OS, IDE, or coding agent) you can always work around it

information flows fine without paid ads, and with much better incentives

> people can pay to have their messages displayed where they will be seen

…why? distribution of information is free across the world, which was not the case a century ago. let the message speak for itself

I ask again, what’s your actual argument against? you’ve seen things through ads you’ve liked? you think people should be allowed to pay to put their thumbs on the scale of the distribution of information? to what end?

this argument is nonsense…I write code on a macbook running macos. it’s not a subscription, but some people also pay a subscription for a proprietary IDE. so any FOSS written with proprietary paid software doesn’t count to you? only if it’s a subscription model?

just fine? what do you think would happen/what’s your actual argument against out of curiosity

- performance is often better, especially on “out of core” (“streaming”, spill to disk data sizes). Polars has done a ton of work on their streaming engine but they’re still catching up

- you don’t need to use Python (but Pythonic wrappers like Ibis exist; disclaimer I worked on Ibis, you can find my blogs on performance comparisons easily there); CLI, WASM, etc. w/o Python

- governance: DuckDB as OSS is setup in a more sustainable way (DuckDB Labs + DuckDB Foundation). while there is a VC-backed company (MotherDuck), it doesn’t employ the primary developers/control the project in the same way the Polars company does

- overall just simplicity and focus. tends to break less, solely focused on single-node, easy to extend, etc. — not trying to do a cloud product, distributing computing, supporting GPU execution

…why do all of those things happen? to sell paid digital advertisement. remove that incentive and I suspect the “social media” problems largely go away

I was expecting this link: https://en.wikipedia.org/wiki/Apple%E2%80%93FBI_encryption_d...

still doesn’t really prove much

you can set breakpoint() to open an IPython REPL with whatever customizations you want (e.g. I turn on vim keybindings)

I was not aware you shouldn’t do that — what’s the rationale/historical context?

a few reasons:

- agents tend to need (already have) a filesystem anyway to be useful (not technically required but generally true, they’re already running somewhere with a filesystem)

- LLMs have a ton of CLI/filesystem stuff in their training data, while MCP is still pretty new (FUSE is old and boring)

- MCP tends to bloat context (not necessarily true but generally true)

UNIX philosophy is really compelling (moreso than MCP being bad). if you can turn your context into files, agents likely “just work” for your use case

that’s not what I said. you honestly seem like you just want to argue about stuff (e.g. not elaborating on the “no” when I basically repeated and agreed with what you said). and you seem to consistently miss my point (in the second part of your response; I’m saying these non-deterministic neural networks are already widespread in industry with these regulations, and it’s fine. they can be explained despite your repeated assertions they cannot be. also the entire point on CPUs which you may have noticed I dropped from my responses because you seemed distracted arguing about it). this is not productive and we’re both clearly stubborn, glhf

> OpenAI's GPT 5.2 is using the same base model as 4o

where’s that info from?

I think we agree then? the tech is useful; you need systems around them (like sandboxes and commit hooks that prevent leaking secrets) to use them effectively (along with learned skills)

very little software (or hardware) used in production is formally verified. tons of non-deterministic software (including neural networks) are operating in production just fine, including in heavily regulated sectors (banking, health care)

…what is your point exactly (and concisely)? I’m saying it doesn’t matter it’s probabilistic, everything is, the tech is still useful

not the same person but in the flow of doing things those little pauses (tens of milliseconds) do matter. I open/close nvim (and less-so tmux) a ton, and run lots of commands per day. I don’t want to wait

and once you get used to things being that fast, it’s hard to go back (analogous to what people say about high-refresh screens/monitors)

all that said the speed of the default mac terminal (and other emulators I tried) was always fine for me, performance was not why I switched to Ghostty

I was pointing out one screenshot from twitter isn’t proof of anything just to be clear; it’s a silly way to make a point.

yes AI makes leaking keys on GH more prevalent, but so what? it’s the same problem as before with roughly the same solution

I’m saying neural networks being probabilistic doesn’t matter — everything is probabilistic. you can still practically use the tools to great effect, just like we use everything else that has underlying probabilities

OpenAI did not have to describe it as sycophancy, they chose to, and I’d contend it was a stupid choice

and yes, you can explain what went wrong just like you can with CPUs. we don’t (usually) talk about quantum-level physics when discussing CPUs; talking about neurons in LLMs is the wrong level of abstraction

I’m not understanding your point… (and would be genuinely curious to)? the models and systems around them have evolved and gotten better (over the past few years for LLMs and decades for “AI” more broadly)

oh I think I do get your point now after a few rereads (correct if wrong but you’re saying it should keep getting better until there’s nothing for us to do). “AI”, and computer systems more broadly, are not and cannot be viable systems. they don’t have agency (ironically) to affect change in their environment (without humans in the loop). computer systems don’t exist/survive without people. all the human concerns around what/why remain, AI is just another tool in a long line of computer systems that make our lives easier/more efficient

like my other comment, my point is one screenshot from twitter vs one anecdote. neither proves anything. cool snarky response though!

you could find tons of API keys on GitHub before these “agentic” tools too. that was my point, one screenshot from twitter vs one anecdote from me. I don’t think either proves the point, but posting a screenshot from twitter like it’s proof of some widespread problem is what I was responding to (N=2, 1 vs 1)

my point is more “skill issue” than “trust me this never happens”

my point on CPUs is people who don’t understand LLMs talk like “hallucinations” are a real thing — LLMs are “deciding” to make stuff up rather than just predicting the next token. yes it’s probabilistic, so is practically everything else at scale. yet it works and here we are. can you really explain in detail how everything you use works? I’m guessing I can explain failure modes of agentic systems (and how to avoid them so you don’t look silly on twitter/github) and how neural networks work better than most people can explain the technology they use every day

I think you’re correct. the reproduction isn’t very precise and the solution doesn’t seem right (I’m not seeing anything about the non-standard pages not being freed). I’d guess this was ignored because it was wrong…

I started heavy usage in April 2025 (Codex CLI -> some Claude Code and trying other CLIs + a bit of Cursor -> Warp.dev -> Claude Code) and I’m still learning as well (and constantly trying to get more efficient)

(I had been using GitHub Copilot for 5+ years already, started as an early beta tested, but I don’t really consider that the same)

I like to say it’s like learning a programming language. it takes time, but you start pattern matching and knowing what works. it took me multiple attempts and a good amount of time to learn Rust, learning effective use of these tools is similar

I’ve also learned a ton across domains I otherwise wouldn’t have touched

you’re just repeating the straw man. if you can’t think critically and just regurgitate every dumb thing you hear idk what to tell you. nobody serious thinks a “singularity” is coming. there’s not even a proper definition of “AGI”

your argument amounts to “some people said stupid shit one time and I took it seriously”

I have tons of examples of AI not committing secrets. this is one screenshot from twitter? I don’t think it makes your point

CPUs are billions of transistors. sometimes one fails and things still work. “probabilistic quicksand” isn’t the dig you think it is to people who know how this stuff works

this is a straw man, nobody serious is promising that. it is a skill like any other that requires learning

(i.e. competitors can still use Claude models but haven’t achieved the same DevEx as CC so far, at least in my opinion and many others)

also while I was initially on the “they should open source” boat, and I’m happy Codex CLI did, there are a ton of benefits to keeping to closed source. just look at how much spam and dumb community drama OpenAI employees now have to deal with on GitHub. I increasingly think it’s a smart moved to keep it closed source and iterate without as direct community involvement on the codebase for now

in this case they’re just British mate

how so?