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

121–130 of 706 posts

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

#121

Post by acedTrex »

cambaceres wrote: post #76
benterix wrote: post #29

Earlier quoted context omitted.

> it's not clear if the value actually exists here. 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. I will give it another run in 6-8 months though.

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.

I have yet to get it to generate code past 10ish lines that I am willing to accept. I read stuff like this and wonder how low yall's standards are, or if you are working on projects that just do not matter in any real world sense.

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

#122

Post by orra »

GenerocUsername wrote: post #112
rs186 wrote: post #104

Earlier quoted context omitted.

3X if not 10X if you are starting a new project with Next.js, React, Tailwind CSS for a fullstack website development, that solves an everyday problem. Yeah I just witnessed that yesterday when creating a toy project. For my company's codebase, where we use internal tools and proprietary technology, solving a problem that does not exist outside the specific domain, on a codebase of over 1000 files? No way. Even locat…

Your first week of AI usage should be crawling your codebase and generating context.md docs that can then be fed back into future prompts so that AI understands your project space, packages, apis, and code philosophy. I guarantee your internal tools are not revolutionary, they are just unrepresented in the ML model out of the box

That sounds incredibly boring.

Is it effective? If so I'm sure we'll see models to generate those context.md files.

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

#123

Post by MattGaiser »

rs186 wrote: post #104
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.

3X if not 10X if you are starting a new project with Next.js, React, Tailwind CSS for a fullstack website development, that solves an everyday problem. Yeah I just witnessed that yesterday when creating a toy project. For my company's codebase, where we use internal tools and proprietary technology, solving a problem that does not exist outside the specific domain, on a codebase of over 1000 files? No way. Even locat…

Yeah, anecdotally it is heavily dependent on:

1. Using a common tech. It is not as good at Vue as it is at React.

2. Using it in a standard way. To get AI to really work well, I have had to change my typical naming conventions (or specify them in detail in the instructions).

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

#124

Post by spicyusername »

acedTrex wrote: post #121
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.

I have yet to get it to generate code past 10ish lines that I am willing to accept. I read stuff like this and wonder how low yall's standards are, or if you are working on projects that just do not matter in any real world sense.

4/5 times I can easily get 100s of lines output, that only needs a quick once over.

1/5 times, I spend an extra hour tangled in code it outputs that I eventually just rewrite from scratch.

Definitely a massive net positive, but that 20% is extremely frustrating.

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

#125

Post by agotterer »

jasonthorsness wrote: post #4
tankenmate wrote: post #3

This is definitely good to have this as an option but at the same time having more context reduces the quality of the output because it's easier for the LLM to get "distracted". So, I wonder what will happen to the quality of code produced by tools like Claude Code if users don't properly understand the trade off being made (if they leave it in auto mode of coding right up to the auto compact).

What do you recommend doing instead? I've been using Claude Code a lot but am still pretty novice at the best practices around this.

I use the main Claude code thread (I don’t know what to call it) for planning and then explicitly tell Claude to delegate certain standalone tasks out to subagents. The subagents don’t consume the main threads context window. Even just delegating testing, debugging, and building will save a ton context.

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

#126

Post by handfuloflight »

sdesol wrote: post #118
handfuloflight wrote: post #107

Earlier quoted context omitted.

Doesn't Claude Code do all of this automatically?

I haven't looked at Claud Code, so I don't know if they have analyzers or not that understands how to extract any type of data other than specific coding data that it is trained on. Based on the runtime for some tasks, I would not be surprised if it is going through all the files and asking "is this relevant" My tool is mainly targeted at massive code bases and enterprise as I still believe the most efficient way to…

Well you should look at it, because it's not going through all files. I looked at your product and the workflow is essentially asking me to do manually what Claude Code does auto. Granted, manually selecting the context will probably lead to lower costs in any case because Claude Code invokes tool calls like grep to do its search, so I do see merit in your product in that respect.

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

#127

Post by mike_hearn »

rs186 wrote: post #104
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.

3X if not 10X if you are starting a new project with Next.js, React, Tailwind CSS for a fullstack website development, that solves an everyday problem. Yeah I just witnessed that yesterday when creating a toy project. For my company's codebase, where we use internal tools and proprietary technology, solving a problem that does not exist outside the specific domain, on a codebase of over 1000 files? No way. Even locat…

My codebase has about 1500 files and is highly domain specific: it's a tool for shipping desktop apps[1] that handles all the building, packaging, signing, uploading etc for every platform on every OS simultaneously. It's written mostly in Kotlin, and to some extent uses a custom in-house build system. The rest of the build is Gradle, which is a notoriously confusing tool. The source tree also contains servers, command line tools and a custom scripting language which is used for all the scripting needs of the project [2].

The code itself is quite complex and there's lots of unusual code for munging undocumented formats, speaking undocumented protocols, doing cryptography, Mac/Windows specific APIs, and it's all built on a foundation of a custom parallel incremental build system.

In other words: nightmare codebase for an LLM. Nothing like other codebases. Yet, Claude Code demolishes problems in it without a sweat.

I don't know why people have different experiences but speculating a bit:

1. I wrote most of it myself and this codebase is unusually well documented and structured compared to most. All the internal APIs have full JavaDocs/KDocs, there are extensive design notes in Markdown in the source tree, the user guide is also part of the source tree. Files, classes and modules are logically named. Files are relatively small. All this means Claude can often find the right parts of the source within just a few tool uses.

2. I invested in making a good CLAUDE.md and also wrote a script to generate "map.md" files that are at the top of every module. These map files contain one-liners of what every source file contains. I used Gemini to make these due to its cheap 1M context window. If Claude does struggle to find the right code by just reading the context files or guessing, it can consult the maps to locate the right place quickly.

3. I've developed a good intuition for what it can and cannot do well.

4. I don't ask it to do big refactorings that would stress the context window. IntelliJ is for refactorings. AI is for writing code.

[1] https://hydraulic.dev

[2] https://hshell.hydraulic.dev/

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

#129

Post by didibus »

photon_lines wrote: post #110
sdesol wrote: post #72

Earlier quoted context omitted.

LLMs (current implementation) are probabilistic so it really needs the actual code to predict the most likely next tokens. Now loading the whole code base can be a problem in itself, since other files may negatively affect the next token.

Sorry -- I keep seeing this being used but I'm not entirely sure how it differs from most of human thinking. Most human 'reasoning' is probabilistic as well and we rely on 'associative' networks to ingest information. In a similar manner - LLMs use association as well -- and not only that, but they are capable of figuring out patterns based on examples (just like humans are) -- read this paper for context: https://ar…

You seem possibly more knowledgeable then me on the matter.

My impression is that LLMs predict the next token based on the prior context. They do that by having learned a probability distribution from tokens -> next-token.

Then as I understand, the models are never reasoning about the problem, but always about what the next token should be given the context.

The chain of thought is just rewarding them so that the next token isn't predicting the token of the final answer directly, but instead predicting the token of the reasoning to the solution.

Since human language in the dataset contains text that describes many concepts and offers many solutions to problems. It turns out that predicting the text that describes the solution to a problem often ends up being the correct solution to the problem. That this was true was kind of a lucky accident and is where all the "intelligence" comes from.

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

#130

Post by wiremine »

cambaceres wrote: post #76
benterix wrote: post #29

Earlier quoted context omitted.

> it's not clear if the value actually exists here. 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. I will give it another run in 6-8 months though.

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 make those tools effective.

It's sort of like we're dropping trucks and airplanes on a generation that only knows walking and bicycles.

If you've never driven a truck before, you're going to crash a few times. Then it's easy to say "See, I told you, this new fangled truck is rubbish."

Those who practice with the truck are going to get the hang of it, and figure out two things:

1. How to drive the truck effectively, and

2. When NOT to use the truck... when talking or the bike is actually the better way to go.

We need to shift the conversation to techniques, and away from the tools. Until we do that, we're going to be forever comparing apples to oranges and talking around each other.

Post reply on HN