Live data from Hacker News

Claude now has access to a server-side container environment

anthropic.com

171–180 of 363 posts

Re: Claude now has access to a server-side container environment

#171
post #28

Earlier quoted context omitted.

I hesitate to use phrases like "bait and switch" but it seems like every model gets released and is borderline awe-inspiring, then as adoption increases, and load increases, it's like it gets hit in the head with a hammer and is basically useless for anything beyond a multi-step google search.

I think it's a psychological bias of some sort. When the feeling of newness wears off and you realize the model is still kind of shit, you have an imperfect memory of the first few uses when you were excited and have repressed the failures from that period. As the hype wears off you become more critical and correctly evaluate the model

It's not because it's actually tracked and even acknowledged by the companies themselves.

Re: Claude now has access to a server-side container environment

#172
post #4

Earlier quoted context omitted.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

I don’t think you’re crazy, something is off in their models. As an example I’ve been using an MCP tool to provide table schemas to Claude for months. There was a point where it stopped recognizing the tool unless mentioned in early August. Maybe that’s related to their degraded quality issue. This morning after pulling the correct schema info Sonnet started hallucinating columns (from Shopify’s API docs) and added t…

FWIW I strongly recommend using some of the recent, good Chinese OSS models. I love GLM-4.5, and Kimi K2 0905 is quite good as well.

Re: Claude now has access to a server-side container environment

#173
post #28

Earlier quoted context omitted.

I hesitate to use phrases like "bait and switch" but it seems like every model gets released and is borderline awe-inspiring, then as adoption increases, and load increases, it's like it gets hit in the head with a hammer and is basically useless for anything beyond a multi-step google search.

I think it's a psychological bias of some sort. When the feeling of newness wears off and you realize the model is still kind of shit, you have an imperfect memory of the first few uses when you were excited and have repressed the failures from that period. As the hype wears off you become more critical and correctly evaluate the model

I get that it’s fun and stylish to tell people they aren’t aware of their own cognitive biases, but it’s also a difficult take to falsify, which is why I generally have a high bar for people to clear when they want to assert that something is all in people’s heads.

People seem to turn to this with a lot when the suspicion many people have is difficult to verify. And while I don’t trust a suspicion just because it’s held by a lot of people, I also won’t allow myself to embrace the comforting certainty of “it’s surely false and it’s psychological bias”.

Sometimes we just need to not be sure what’s going on.

Re: Claude now has access to a server-side container environment

#174
post #4

Earlier quoted context omitted.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

I don’t think you’re crazy, something is off in their models. As an example I’ve been using an MCP tool to provide table schemas to Claude for months. There was a point where it stopped recognizing the tool unless mentioned in early August. Maybe that’s related to their degraded quality issue. This morning after pulling the correct schema info Sonnet started hallucinating columns (from Shopify’s API docs) and added t…

ive been thinking its that my company mcp has blown up in context size, but using claude without claude code, i get context window overflows constantly now.

another option could be a system prompt change to make it too long?

Re: Claude now has access to a server-side container environment

#175
post #98

Earlier quoted context omitted.

Yeah in agent mode it compiles code and runs tests, if anything breaks it attempts to fix. Kinda wild to see at first.

In agent mode there is a whitelist of commands in the VScode settings that it can do without confirmation. When I went to edit that file, copilot suggested adding "rm -rf *".

This must be a mistake. It should be "rm -rf /*"

Re: Claude now has access to a server-side container environment

#177
post #69

Earlier quoted context omitted.

nay. When you use claude long enough, you'd find yourself spending more time refactoring than coding lol

the fuck you doing that by hand for?

because the models will fuck it up :)

they're great for spitting out a lot of code but not so great at making it work or make sense, unfortunately

Re: Claude now has access to a server-side container environment

#178
post #4
post #3

They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

Here's a useful tracker for how "stupid" the models are now and over some preset time periods: https://aistupidlevel.info

Re: Claude now has access to a server-side container environment

#179
post #6

One step closer to mass unemployment, yay!

You mean mass employment?

With the amount of slop/trash LLMs produce so quickly, we are gonna need even devs coming out of retirement to fix the unmaintainable trash that's been created now!

Every 10k tokens vibe kiddies spend is another retiree developer summoned to fix their shit.

Re: Claude now has access to a server-side container environment

#180
post #6

One step closer to mass unemployment, yay!

That doesn't make any sense and isn't an appropriate comment for this discussion. The Anthropic product adding a feature is not the end of employment or even a step along the way. MOST PEOPLE can't even use an actual computer yet even think about programming. WYSIWYG editors didn't kill web development because most people are simply too stupid to understand a new tool, let alone use it.

> The Anthropic product adding a feature is not the end of employment or even a step along the way.

I respectfully disagree. Look at the groundbreaking Study Mode added by OpenAI: https://openai.com/index/chatgpt-study-mode/. Teachers are now jobless thanks to that amazing, monumental, revolutionary feature that the genuises at OpenAI added. Every one of their features is AGI.

Post reply on HN