Anthropic's Claude Code's full source code leaked.
-
Anthropic's Claude Code's full source code leaked. Claude is seen by many to be the best coding LLM on the market with Anthropic proudly stating that Claude Code itself is mostly written by the LLM.
Now this sounds good as long as nobody can see the code which is quite the trash fire. Detecting "code sentiment" via regular expressions, variable and functions names containing prompt parts trying to influence the bot, a completely intransparent mess of a control flow that makes actual maintenance and debugging functionally impossible and the prompts ... of the prompts. All the begging and pleading to the chatbot not to do this or not to do that or please to do this.
It is fascinating but it is as far away from actual engineering as drunkenly pissing your name in the snow. Dunno what you call the people prompting software at Anthropic but "engineer" is not it.
Now it is fun to look at the currently hyped product striped bare and showing its pathetic quality but that is the future of software if we let those companies continue to undermine every good practice software engineering has tried establishing.
The software we have to use will be bad, insecure, unmaintainable, expensive with nobody having the skills or resources to build something better. As I wrote a few months ago: LLM based software production is equivalent to saying that fast fashion should be the only way to produce clothing. A tragic degeneration of the quality of the artefacts we rely on build for maximum profit on the backs of people in countries from the global majority.
@tante I know devs that are saying if AI makes them 10-20% more productive it is worth it. And there’s a rejection of the ethical implications of the technology. I’m thankful I’m on the tail end of my career.
-
Anthropic's Claude Code's full source code leaked. Claude is seen by many to be the best coding LLM on the market with Anthropic proudly stating that Claude Code itself is mostly written by the LLM.
Now this sounds good as long as nobody can see the code which is quite the trash fire. Detecting "code sentiment" via regular expressions, variable and functions names containing prompt parts trying to influence the bot, a completely intransparent mess of a control flow that makes actual maintenance and debugging functionally impossible and the prompts ... of the prompts. All the begging and pleading to the chatbot not to do this or not to do that or please to do this.
It is fascinating but it is as far away from actual engineering as drunkenly pissing your name in the snow. Dunno what you call the people prompting software at Anthropic but "engineer" is not it.
Now it is fun to look at the currently hyped product striped bare and showing its pathetic quality but that is the future of software if we let those companies continue to undermine every good practice software engineering has tried establishing.
The software we have to use will be bad, insecure, unmaintainable, expensive with nobody having the skills or resources to build something better. As I wrote a few months ago: LLM based software production is equivalent to saying that fast fashion should be the only way to produce clothing. A tragic degeneration of the quality of the artefacts we rely on build for maximum profit on the backs of people in countries from the global majority.
@tante but it's the AI Overlord god code it's not meant to be understood by meat sacks ...
-
@tante might well be the event that will make the bubble-popping begin. especially because its so far away from the values that anthropic tries so hard to project.
-
J jeppe@uddannelse.social shared this topic
-
Anthropic's Claude Code's full source code leaked. Claude is seen by many to be the best coding LLM on the market with Anthropic proudly stating that Claude Code itself is mostly written by the LLM.
Now this sounds good as long as nobody can see the code which is quite the trash fire. Detecting "code sentiment" via regular expressions, variable and functions names containing prompt parts trying to influence the bot, a completely intransparent mess of a control flow that makes actual maintenance and debugging functionally impossible and the prompts ... of the prompts. All the begging and pleading to the chatbot not to do this or not to do that or please to do this.
It is fascinating but it is as far away from actual engineering as drunkenly pissing your name in the snow. Dunno what you call the people prompting software at Anthropic but "engineer" is not it.
Now it is fun to look at the currently hyped product striped bare and showing its pathetic quality but that is the future of software if we let those companies continue to undermine every good practice software engineering has tried establishing.
The software we have to use will be bad, insecure, unmaintainable, expensive with nobody having the skills or resources to build something better. As I wrote a few months ago: LLM based software production is equivalent to saying that fast fashion should be the only way to produce clothing. A tragic degeneration of the quality of the artefacts we rely on build for maximum profit on the backs of people in countries from the global majority.
Salesforce has Agentforce Vibes and if you have access to it you can see a lot of the prompts they wrote to guide the LLM. There's very little to stop you from copying it all.
It's the same with a lot of their agentic offerings, you can look under the hood and customise how it works. All they're selling you is a prompt library and the ability to run the LLM on their infrastructure.
https://www.salesforce.com/agentforce/developers/vibe-coding/
-
Anthropic's Claude Code's full source code leaked. Claude is seen by many to be the best coding LLM on the market with Anthropic proudly stating that Claude Code itself is mostly written by the LLM.
Now this sounds good as long as nobody can see the code which is quite the trash fire. Detecting "code sentiment" via regular expressions, variable and functions names containing prompt parts trying to influence the bot, a completely intransparent mess of a control flow that makes actual maintenance and debugging functionally impossible and the prompts ... of the prompts. All the begging and pleading to the chatbot not to do this or not to do that or please to do this.
It is fascinating but it is as far away from actual engineering as drunkenly pissing your name in the snow. Dunno what you call the people prompting software at Anthropic but "engineer" is not it.
Now it is fun to look at the currently hyped product striped bare and showing its pathetic quality but that is the future of software if we let those companies continue to undermine every good practice software engineering has tried establishing.
The software we have to use will be bad, insecure, unmaintainable, expensive with nobody having the skills or resources to build something better. As I wrote a few months ago: LLM based software production is equivalent to saying that fast fashion should be the only way to produce clothing. A tragic degeneration of the quality of the artefacts we rely on build for maximum profit on the backs of people in countries from the global majority.
@tante but why does it work better than the other machines then?
-
@tante I know devs that are saying if AI makes them 10-20% more productive it is worth it. And there’s a rejection of the ethical implications of the technology. I’m thankful I’m on the tail end of my career.
-
@tante but why does it work better than the other machines then?
@Openhuman @tante it doesn't. it's all psychological tricks to make you think it works.
-
Anthropic's Claude Code's full source code leaked. Claude is seen by many to be the best coding LLM on the market with Anthropic proudly stating that Claude Code itself is mostly written by the LLM.
Now this sounds good as long as nobody can see the code which is quite the trash fire. Detecting "code sentiment" via regular expressions, variable and functions names containing prompt parts trying to influence the bot, a completely intransparent mess of a control flow that makes actual maintenance and debugging functionally impossible and the prompts ... of the prompts. All the begging and pleading to the chatbot not to do this or not to do that or please to do this.
It is fascinating but it is as far away from actual engineering as drunkenly pissing your name in the snow. Dunno what you call the people prompting software at Anthropic but "engineer" is not it.
Now it is fun to look at the currently hyped product striped bare and showing its pathetic quality but that is the future of software if we let those companies continue to undermine every good practice software engineering has tried establishing.
The software we have to use will be bad, insecure, unmaintainable, expensive with nobody having the skills or resources to build something better. As I wrote a few months ago: LLM based software production is equivalent to saying that fast fashion should be the only way to produce clothing. A tragic degeneration of the quality of the artefacts we rely on build for maximum profit on the backs of people in countries from the global majority.
-
@vikxin @atax1a I elaborated on that here https://tante.cc/2026/01/15/software-as-fast-fashion/
-
@vikxin @atax1a I elaborated on that here https://tante.cc/2026/01/15/software-as-fast-fashion/
-
A abekonge@venner.network shared this topic
