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

301–310 of 706 posts

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

#301

Post by troupo »

unoti wrote: post #263
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…

> 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. Every success story with AI coding involves giving the agent enough context to succeed on a task that it…

> And every story where it fails is a situation where it had not enough context to see a path to success on.

And you know that because people are actively sharing the projects, code bases, programming languages and approaches they used? Or because your gut feeling is telling you that?

For me, agents failed with enough context, and with not enough context, and succeeded with context, or not enough, and succeeded and failed with and without "guidance and coaching"

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

#302

Post by spanishgum »

daymanstep wrote: post #282
ericmcer wrote: post #275

Earlier quoted context omitted.

Agreed, daily Cursor user. Just got out of a 15m huddle with someone trying to understand what they were doing in a PR before they admitted Claude generated everything and it worked but they weren't sure why... Ended up ripping about 200 LoC out because what Claude "fixed" wasn't even broken. So never let it generate code, but the autocomplete is absolutely killer. If you understand how to code in 2+ languages you ca…

> I have been able to swap to languages I have almost no experience in and work fairly well because memorizing syntax is irrelevant. I do wonder whether your code does what you think it does. Similar-sounding keywords in different languages can have completely different meanings. E.g. the volatile keyword in Java vs C++. You don't know what you don't know, right? How do you know that the AI generated code does what y…

The same way I would with any of my own code - I would test it!

The key here is to spend less time searching, and more time understanding the search result.

I do think the vibe factor is going to bite companies in the long run. I see a lot of vibe code pushed by both junior and senior devs alike, where it's clear not enough time was spent reviewing the product. This behavior is being actively rewarded now, but I do think the attitude around building code as fast as possible will change if impact to production systems becomes realized as a net negative. Time will tell.

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

#303

Post by falcor84 »

varyherb wrote: post #80

I believe this can be configured in Claude Code via the following environment variable: ANTHROPIC_BETAS="context-1m-2025-08-07" claude

Have you tested it? I see that this env var isn't specified in their docs

https://docs.anthropic.com/en/docs/claude-code/settings#envi...

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

#304

Post by not_that_d »

My experience with the current tools so far:

1. It helps to get me going with new languages, frameworks, utilities or full green field stuff. After that I expend a lot of time parsing the code to understand what it wrote that I kind of "trust" it because it is too tedious but "it works".

2. When working with languages or frameworks that I know, I find it makes me unproductive, the amount of time I spend writing a good enough prompt with the correct context is almost the same or more that if I write the stuff myself and to be honest the solution that it gives me works for this specific case but looks like a junior code with pitfalls that are not that obvious unless you have the experience to know it.

I used it with Typescript, Kotlin, Java and C++, for different scenarios, like websites, ESPHome components (ESP32), backend APIs, node scripts etc.

Botton line: usefull for hobby projects, scripts and to prototypes, but for enterprise level code it is not there.

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

#305

Post by oars »

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…

I tell Claude that it wrote XYZ in another session (I wrote it) then use that context to ask questions or make changes.

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

#306

Post by pornel »

jacobr1 wrote: post #291
daymanstep wrote: post #282

Earlier quoted context omitted.

> I have been able to swap to languages I have almost no experience in and work fairly well because memorizing syntax is irrelevant. I do wonder whether your code does what you think it does. Similar-sounding keywords in different languages can have completely different meanings. E.g. the volatile keyword in Java vs C++. You don't know what you don't know, right? How do you know that the AI generated code does what y…

Beyond code-gen I think some techniques are very underutilized. One can generate tests, generate docs, explain things line by line. Explicitly explaining alternative approaches and tradeoffs is helpful too. While, as with everything in this space, there are imperfection, I find a ton of value in looking beyond the code into thinking through the use cases, alternative approaches and different ways to structure the sam…

I've wasted time debugging phantom issues due to LLM-generated tests that were misusing an API.

Brainstorming/explanations can be helpful, but also watch out for Gell-Mann amnesia. It's annoying that LLMs always sound smart whether they are saying something smart or not.

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

#307

Post by m4r71n »

brokegrammer wrote: post #232

Many people are confused about the usefulness of 1M tokens because LLMs often start to get confused after about 100k. But this is big for Claude 4 because it uses automatic RAG when the context becomes large. With optimized retrieval thanks to RAG, we'll be able to make good use of those 1M tokens.

How does this work under the hood? Does it build an in-memory vector database of the input sources and runs queries on top of that data to supplement the context window?

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

#308

Post by troupo »

mstkllah wrote: post #199
dillydogg wrote: post #138

Earlier quoted context omitted.

Whenever I read comments from the people singing their praises of the technology, it's hard not to think of the study that found AI tools made developers slower in early 2025. >When developers are allowed to use AI tools, they take 19% longer to complete issues—a significant slowdown that goes against developer beliefs and expert forecasts. This gap between perception and reality is striking: developers expected AI t…

Ah, the very extensive study with 16 developers. Bulletproof results.

Compared to "it's just a skill issue you're not prompting it correctly" crowd with literally zero actionable data?

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

#309

Post by hirako2000 »

unoti wrote: post #263
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…

> 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. Every success story with AI coding involves giving the agent enough context to succeed on a task that it…

Bold claims.

From my experience, even the top models continue to fail delivering correctness on many tasks even with all the details and no ambiguity in the input.

In particular when details are provided, in fact.

I find that with solutions likely to be well oiled in the training data, a well formulated set of *basic* requirements often leads to a zero shot, "a" perfectly valid solution. I say "a" solution because there is still this probability (seed factor) that it will not honour part of the demands.

E.g, build a to-do list app for the browser, persist entries into a hashmap, no duplicate, can edit and delete, responsive design.

I never recall seeing an LLM kick off C++ code out of that. But I also don't recall any LLM succeeding in all these requirements, even though there aren't that many.

It may use a hash set, or even a set for persistence because it avoids duplicates out of the box. And it would even use a hash map to show it used a hashmap but as an intermediary data structure. It would be responsive, but the edit/delete buttons may not show, or may not be functional. Saving the edits may look like it worked, but did not.

The comparison with junior developers is pale. Even a mediocre developer can test its and won't pretend that it works if it doesn't even execute. If a develop lies too many times it would lose trust. We forgive these machines because they are just automatons with a label on it "can make mistakes". We have no resorts to make them speak the truth, they lie by design.

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

#310

Post by DiabloD3 »

codazoda wrote: post #244
DiabloD3 wrote: post #152

Neat. I do 1M tokens context locally, and do it entirely with a single GPU and FOSS software, and have access to a wide range of models of equivalent or better quality. Explain to me, again, how Anthropic's flawed business model works?

Tell us more?

Nothing really to say, its just like everyone else's inference setups.

Select a model that produces good results, has anywhere from 256k to 1M context (ex: Qwen3-Coder can do 1M), is under one of the acceptable open weights licenses, and run it in llama.cpp.

llama.cpp can split layers between active and MoE, and only load the active ones into vram, leaving the rest of it available for context.

With Qwen3-Coder-30B-A3B, I can use Unsloth's Q4_K_M, consume a mere 784MB of VRAM with the active layers, then consume 27648MB (kv cache) + 3096MB (context) with the kv cache quantized to iq4_nl. This will fit onto a single card with 32GB of VRAM, or slightly spill over on 24GB.

Since I don't personally need that much, I'm not pouring entire projects into it (I know people do this, and more data does not produce better results), I bump it down to 512k context and fit it in 16.0GB, to avoid spill over on my 24GB card. In the event I do need the context, I am always free to enable it.

I do not see a meaningful performance difference between all on the card and MoE sent to RAM while active is on VRAM, its very much a worthwhile option for home inference.

Edit: For completeness sake, 256k context with this configuration is 8.3GB total VRAM, making _very_ budget good inference absolutely possible.

Post reply on HN