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

551–560 of 706 posts

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

#551

Post by cube00 »

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…

> Tell Claude your developer finished XYZ [...] (Claude will find more problems with your developer's work than with yours).

It's crazy to think LLMs are so focused on pleasing us that we have to trick them like this to get frank and fearless feedback.

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

#552

Post by jack_pp »

aliljet wrote: post #16

This is definitely one of my CORE problem as I use these tools for "professional software engineering." I really desperately need LLMs to maintain extremely effective context and it's not actually that interesting to see a new model that's marginally better than the next one (for my day-to-day). However. Price is king. Allowing me to flood the context window with my code base is great, but given that the price has su…

maybe we need LLMs trained on ASTs or create a new symbolic way to represent software that's faster to grok by LLMs and have a translator so we can verify the code

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

#553

Post by ewoodrich »

oceanplexian wrote: post #161
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…

I work in FAANG, have been for over a decade. These tools are creating a huge amount of value, starting with Copilot but now with tools like Claude Code and Cursor. The people doing so don’t have a lot of time to comment about it on HN since we’re busy building things.

I use agentic tools all the time but comments like this always make me feel like someone's trying to sell me their new cryptocoin or NFT.

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

#554

Post by cube00 »

Aeolun wrote: post #452
apimade wrote: post #432

Earlier quoted context omitted.

Many who say LLMs produce “enterprise-grade” code haven’t worked in mid-tier or traditional companies, where projects are held together by duct tape, requirements are outdated, and testing barely exists. In those environments, enterprise-ready code is rare even without AI. For developers deeply familiar with a codebase they’ve worked on for years, LLMs can be a game-changer. But in most other cases, they’re best for…

Umm, Claude Code is a lot better than a lot of enterprise grade code I see. And it actually learns from mistakes with a properly crafted instruction xD

>And it actually learns from mistakes with a properly crafted instruction

...until it hallucinates and ignores said instruction.

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

#555

Post by ewoodrich »

oars wrote: post #305
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.

Hah, I do the same when I need to manually intervene to nudge the solution in the direction I want after a few failed attempts to recontruct my prompt to avoid some undesired path the LLM really wants to go down.

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

#556

Post by adastra22 »

krainboltgreene wrote: post #537
onion2k wrote: post #348

Earlier quoted context omitted.

Large enough repos don't fit on a single machine. I don't believe any human can understand a problem if they need to fit the entire problem blem domain in their head, and the scope of a domain that doesn't fit on a computer. You have to break it down into a manageable amount of information to tackle it in chunks. If a person can do that, so can an LLM prompted to do that by a person.

I have an entire life worth of context and I still remember projects I worked on 15 years ago.

Not with pixel perfect accuracy. You vaguely remember, although it may not feel like that because your brain fills in the details (hallucinates) as you recall. The comparisons are closer than you might think.

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

#557

Post by adastra22 »

joenot443 wrote: post #222
bigmadshoe wrote: post #37

Earlier quoted context omitted.

https://research.trychroma.com/context-rot

This is a good piece. Clearly it's a pretty complex problem and the intuitive result a layman engineer like myself might expect doesn't reflect the reality of LLMs. Regex works as reliably on 20 characters as it does 2m characters; the only difference is speed. I've learned this will probably _never_ be the case with LLMs, there will forever exist some level of epistemic doubt in its result. When they announced Big C…

Depends on the change.

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

#558

Post by mrcwinn »

I wish they’d fix other things faster. Still can’t upload an Excel file in the iOS app, even with analyst mode enabled. The voice mode feels like it’s 10 years behind OpenAI (no realtime, for example). And Opus 4.1 still occasionally goes absolutely mental and provides much worse analysis than o3 or GPT5-thinking.

Rooting for Anthropic. Competition in this space is good.

I watched an interview with Dario recently where he said he wasted a “product guy” and it really shows.

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

#559

Post by darkmarmot »

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 work in distributed systems programming and have been horrified by the crap the AIs produce. I've found them to be quite helpful at summarizing papers and doing research, providing jumping off points. But none of the code I write can be scraped from a blog post.

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

#560

Post by valenterry »

Miraste wrote: post #365
pornel wrote: post #306

Earlier quoted context omitted.

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.

Yes, you can't use any of the heuristics you develop for human writing to decide if the LLM is saying something stupid, because its best insights and its worst hallucinations all have the same formatting, diction, and style. Instead, you need to engage your frontal cortex and rationally evaluate every single piece of information it presents, and that's tiring.

It's like listening to a politician or lawyer, who might talk absolute bullshit in the most persuading words. =)
Post reply on HN