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

Claude Sonnet 4 now supports 1M tokens of context

anthropic.com

Post reply on HN
Print view View original

251–260 of 706 posts

Re: Claude Sonnet 4 now supports 1M tokens of context

#251

Post by oceanplexian »

wiremine wrote: post #130
cambaceres wrote: post #76

Earlier quoted context omitted.

For me it’s meant a huge increase in productivity, at least 3X. Since so many claim the opposite, I’m curious to what you do more specifically? I guess different roles/technologies benefit more from agents than others. I build full stack web applications in node/.net/react, more importantly (I think) is that I work on a small startup and manage 3 applications myself.

> Having spent a couple of weeks on Claude Code recently, I arrived to the conclusion that the net value for me from agentic AI is actually negative. > For me it’s meant a huge increase in productivity, at least 3X. How do we reconcile these two comments? I think that's a core question of the industry right now. My take, as a CTO, is this: we're giving people new tools, and very little training on the techniques that…

It's pretty simple, AI is now political for a lot of people. Some folks have a vested interest in downplaying it or over hyping it rather than impartially approaching it as a tool.

Re: Claude Sonnet 4 now supports 1M tokens of context

#252

Post by cmdli »

weego wrote: post #187
wiremine wrote: post #130

Earlier quoted context omitted.

> Having spent a couple of weeks on Claude Code recently, I arrived to the conclusion that the net value for me from agentic AI is actually negative. > For me it’s meant a huge increase in productivity, at least 3X. How do we reconcile these two comments? I think that's a core question of the industry right now. My take, as a CTO, is this: we're giving people new tools, and very little training on the techniques that…

In a similar role and place with this. My biggest take so far: If you're a disciplined coder that can handle 20% of an entire project's (project being a bug through to an entire app) time being used on research, planning and breaking those plans into phases and tasks, then augmenting your workflow with AI appears to be to have large gains in productivity. Even then you need to learn a new version of explaining it 'ou…

My experience has been entirely the opposite as an IC. If I spend the time to delve into the code base to the point that I understand how it works, AI just serves as a mild improvement in writing code as opposed to implementing it normally, saving me maybe 5 minutes on a 2 hour task.

On the other hand, I’ve found success when I have no idea how to do something and tell the AI to do it. In that case, the AI usually does the wrong thing but it can oftentimes reveal to me the methods used in the rest of the codebase.

Re: Claude Sonnet 4 now supports 1M tokens of context

#253

Post by chasd00 »

wiremine wrote: post #130
cambaceres wrote: post #76

Earlier quoted context omitted.

For me it’s meant a huge increase in productivity, at least 3X. Since so many claim the opposite, I’m curious to what you do more specifically? I guess different roles/technologies benefit more from agents than others. I build full stack web applications in node/.net/react, more importantly (I think) is that I work on a small startup and manage 3 applications myself.

> Having spent a couple of weeks on Claude Code recently, I arrived to the conclusion that the net value for me from agentic AI is actually negative. > For me it’s meant a huge increase in productivity, at least 3X. How do we reconcile these two comments? I think that's a core question of the industry right now. My take, as a CTO, is this: we're giving people new tools, and very little training on the techniques that…

One thing to think about is many software devs have a very hard time with code they didn't write. I've seen many devs do a lot of work to change code to something equivalent (even with respect to performance and readability) only because it's not the way they would have done it. I could see people having a hard time using what the LLM produced without having to "fix it up" and basically re-write everything.

Re: Claude Sonnet 4 now supports 1M tokens of context

#254

Post by qwertox »

> desperately need LLMs to maintain extremely effective context

Last time I used Gemini it did something very surprising: instead of providing readable code, it started to generate pseudo-minified code.

Like on CSS class would become one long line of CSS, and one JS function became one long line of JS, with most of the variable names minified, while some remained readable, but short. It did away with all unnecessary spaces.

I was asking myself what is happening here, and my only explanation was that maybe Google started training Gemini on minified code, on making Gemini understand and generate it, in order to maximize the value of every token.

Re: Claude Sonnet 4 now supports 1M tokens of context

#255

Post by dghlsakjg »

jeremy_k wrote: post #224
croes wrote: post #155

Earlier quoted context omitted.

Do you only skim the results or do you audit them at some point to prevent security issues?

What kind of security issues are you thinking about? I'm generating UI components like Selects for certain data types or Charts of data.

User input is a notoriously thorny area.

If you aren't sanitizing and checking the inputs appropriately somewhere between the user and trusted code, you WILL get pwned.

Rails provides default ways to avoid this, but it makes it very easy to do whatever you want with user input. Rails will not necessarily throw a warning if your AI decides that it wants to directly interpolate user input into a sql query.

Re: Claude Sonnet 4 now supports 1M tokens of context

#256

Post by bgilly »

seperman wrote: post #235
gdudeman wrote: post #83

A tip for those who both use Claude Code and are worried about token use (which you should be if you're stuffing 400k tokens into context even if you're on 20x Max): 1. Build context for the work you're doing. Put lots of your codebase into the context window. 2. Do work, but at each logical stopping point hit double escape to rewind to the context-filled checkpoint. You do not spend those tokens to rewind to that po…

Very interesting. Why does Claude find more problems if we mention the code is written by another developer?

In my experience, Claude will criticize others more than it will criticize itself. Seems similar to how LLMs in general tend to say yes to things or call anything a good idea by default.

I find it to be an entertaining reflection of the cultural nuances embedded into training data and reinforcement learning processes.

Re: Claude Sonnet 4 now supports 1M tokens of context

#257

Post by jorvi »

GodelNumbering wrote: post #201
verall wrote: post #151

Earlier quoted context omitted.

> This week, I used it to write ESP32 firmware and a Linux kernel driver. I'm not meaning to be negative at all, but was this for a toy/hobby or for a commercial project? I find that LLMs do very well on small greenfield toy/hobby projects but basically fall over when brought into commercial projects that often have bespoke requirements and standards (i.e. has to cross compile on qcc, comply with autosar, in-house bu…

This is my experience too. Also, their propensity to jump into code without necessarily understanding the requirement is annoying to say the least. As the project complexity grows, you find yourself writing longer and longer instructions just to guardrail. Another rather interesting thing is that they tend to gravitate towards sweep the errors under the rug kind of coding which is disastrous. e.g. "return X if we don…

Running LLM code with kernel privileges seems like courting disaster. I wouldn't dare do that unless I had a rock-solid grasp of the subsystem, and at that point, why not just write the code myself? LLM coding is on-average 20% slower.

Re: Claude Sonnet 4 now supports 1M tokens of context

#258

Post by dennisy »

wiremine wrote: post #130
cambaceres wrote: post #76

Earlier quoted context omitted.

For me it’s meant a huge increase in productivity, at least 3X. Since so many claim the opposite, I’m curious to what you do more specifically? I guess different roles/technologies benefit more from agents than others. I build full stack web applications in node/.net/react, more importantly (I think) is that I work on a small startup and manage 3 applications myself.

> Having spent a couple of weeks on Claude Code recently, I arrived to the conclusion that the net value for me from agentic AI is actually negative. > For me it’s meant a huge increase in productivity, at least 3X. How do we reconcile these two comments? I think that's a core question of the industry right now. My take, as a CTO, is this: we're giving people new tools, and very little training on the techniques that…

Also another view is that developers below a certain level get a positive benefit and those above get a negative effect.

This makes sense, as the models are an average of the code out there and some of us are above and below that average.

Sorry btw I do not want to offend anyone who feels they do garner a benefit from LLMs, just wanted to drop in this idea!

Re: Claude Sonnet 4 now supports 1M tokens of context

#260

Post by mcintyre1994 »

seperman wrote: post #235
gdudeman wrote: post #83

A tip for those who both use Claude Code and are worried about token use (which you should be if you're stuffing 400k tokens into context even if you're on 20x Max): 1. Build context for the work you're doing. Put lots of your codebase into the context window. 2. Do work, but at each logical stopping point hit double escape to rewind to the context-filled checkpoint. You do not spend those tokens to rewind to that po…

Very interesting. Why does Claude find more problems if we mention the code is written by another developer?

Total guess, but maybe it breaks it out of the sycophancy that most models seem to exhibit?

I wonder if they’d also be better at things like telling you an idea is dumb if you tell it it’s from someone else and you’re just assessing it.

Post reply on HN