Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code Unpacked : A visual guide

ccunpacked.dev

Post reply on HN
Print view View original

331–340 of 464 posts

Re: Claude Code Unpacked : A visual guide

#331

Post by skeledrew »

amangsingh wrote: post #189
bogdanoff_2 wrote: post #180

Earlier quoted context omitted.

What do you mean by "actually governing the agents at the system level", and how is it different from "herding cats"?

Herding cats is treating the LLM's context window as your state machine. You're constantly prompt-engineering it to remember the rules, hoping it doesn't hallucinate or silently drop constraints over a long session. System-level governance means the LLM is completely stripped of orchestration rights. It becomes a stateless, untrusted function. The state lives in a rigid, external database (like SQLite). The database…

> The database dictates the workflow, hands the LLM a highly constrained task, and runs external validation on the output before the state is ever allowed to advance.

This sounds like where lat.md[0] is headed. Only thing is it doesn't do task constraint. Generally I find the path these tools are taking interesting.

[0] https://github.com/1st1/lat.md

Re: Claude Code Unpacked : A visual guide

#332

Post by saulpw »

vntok wrote: post #288
kordlessagain wrote: post #269

Earlier quoted context omitted.

Guess what? People have ZERO reason to Open Source anything now.

Why would you think that?

I'm a committed open source dev and I've flipped my own switch from "default public" to "default private".

Re: Claude Code Unpacked : A visual guide

#333

Post by skeledrew »

amangsingh wrote: post #314
fallinditch wrote: post #199

Earlier quoted context omitted.

Sounds good, I'll keep an eye out.

Just dropped the Show HN here: https://news.ycombinator.com/item?id=47601608 . Would love to hear your thoughts on the architecture!

There's nothing at that link. Not even a title.

Re: Claude Code Unpacked : A visual guide

#334

Post by msully4321 »

samusiam wrote: post #260
oblio wrote: post #251

Earlier quoted context omitted.

At least Gemini and Claude constantly break down with scrolling in various Linux terminals, something which was solved by countless TUIs decades ago. I think a lot of the people prasing Claude & co are on Macs.

I haven't seen the scrolling glitch in months, where previously it was happening multiple times a day. Also haven't seen anyone complain about it in quite some time. Pretty sure they have resolved that.

They have not! If I am scrolled up while more output is produced, the scrollback jumps to the top pretty consistently.

Re: Claude Code Unpacked : A visual guide

#335

Post by woodson »

abossy wrote: post #325
jayd16 wrote: post #313

Earlier quoted context omitted.

Why are "tools" for local IO interesting and not just the only way to do it? I can't really imagine a server architecture that gets to read your local files and present them without a fat client of some kind. What is the naive implementation you're comparing against? Ssh access to the client machine?

It's early days and we don't fully understand LLM behavior to the extent that we can assume questions like this about agent design are resolved. For instance, is an agent smarter with Claude Code's tools or `exec_command` like Codex? And does that remain true for each subsequent model release?

It’s a distinction that IMHO likely doesn’t make much difference, at least for the mostly automated/non-interactive coding agent use case. What matters more is how well the post-training on synthetic harness traces works.

Re: Claude Code Unpacked : A visual guide

#337

Post by apeace »

Pardon me, but I think it's rather obvious that it worked this way?

The real value of Anthropic is in the models that they spent hundreds of millions training. Anyone can build a frontend that does a loop, using the model to call tools and accomplish a task. People do it every day.

Sure, they've worked hard to perfect this particular frontend. But it's not like any of this is revolutionary.

Re: Claude Code Unpacked : A visual guide

#338

Post by anthk »

000ooo000 wrote: post #95
troupo wrote: post #80

Earlier quoted context omitted.

They explicitly boast about using claude code to write code: https://x.com/bcherny/status/2007179836704600237 That's how you get "oh this TUI API wrapper needs 68GB of RAM" https://x.com/jarredsumner/status/2026497606575398987 or "we need 16ms to lay out a few hundred characters on screen that's why it's a small game engine": https://x.com/trq212/status/2014051501786931427

Just finished looking at Ink here.. frontend world has no shame. Love the gloating about 40x less RAM as if that amount of memory for a text REPL even approaches defensible. "CC built CC" is not the flex people seem to suggest it is.

Frontend losers not realizing the turds they are releasing. An LLM client fits under netcat+echo+awk+jq runnable under a 486 if there's no SSL/TLS on its way, Pentium II could drive fast TLS connections like nothing and under 32MB of RAM with NetBSD for a simple terminal install, maybe with X and a simple WM with RXVT if you care.

Re: Claude Code Unpacked : A visual guide

#340

Post by anthk »

troupo wrote: post #257
hombre_fatal wrote: post #215

Earlier quoted context omitted.

They just claimed that you can build a 3D game in 500k loc, thus Claude Code shouldn't use so many loc. They/you didn't render the argument for that. For example, without looking at the code, the superstition also works in the opposite direction: Claude Code is an interface to using AI to do any computer task while a 3D game just lets you shoot some bad guys, so surely the 3D game must be done in fewer loc. That's eq…

> Claude Code is an interface to using AI to do any computer task Claude Code is quite literally a wrapper around a few APIs. At one point it needed 68GB of RAM to run and requires 11ms to "lay a scene graph" to display a few hundred characters on screen. All links here: https://news.ycombinator.com/item?id=47598488 > while a 3D game just lets you shoot some bad guys, so surely the 3D game must be done in fewer loc.…

I could run a text adventure with a Zmachine emulator under a 6502 based machine and 48k of RAM, with Ozmoo you can play games like Tristam Island. On a Commodore 64, or an Apple II for you US commenters. I repeat the game it's being emulated in a simple computer with barely more processing power than a current keyboard controller.

As the ZMachine interpreter (V3 games at least, enough for the mentioned example), even a Game Boy used to play Pokemon Red/Blue -and Crystal/Sylver/Blue, just slightly better specs than the OG GB- can run Tristam Island with keypad based input picking both selected words from the text or letter by letter as when you name a character in an RPG. A damn Game Boy, a pocket console from 1989. Not straightly running a game, again. Emulating a simple text computer -the virtual machine- to play it. No slowdowns, no-nothing, and you can save the game (the interpreter status) in a battery backed cartridge, such as the Everdrive. Everything under... 128k.

Claude Code and the rest of 'examples' it's what happens when trade programmers call themselves 'engineers' without even a CS degree.

Post reply on HN