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

681–690 of 706 posts

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

#681

Post by gerhardi »

jimbokun wrote: post #665
vidarh wrote: post #600

Earlier quoted context omitted.

The comparison would be apt if the LLM was trained on your codebase .

Isn’t that the problem? I don’t see any progress on incrementally training LLMs on specific projects. I believe it’s called fine tuning, right? Why isn’t that the default approach anywhere instead of the hack of bigger “context windows”?

I’m not well versed enough on this but wouldn’t it be a problem with custom training that the specific project training codebases probably would likely have a lot of the implemented stuff, relevant for the domain, only once and in one way, compared to how the todays popular large models have been trained maybe with countless different ways to use common libraries for whatever various tasks with whatever Github ripped material fed in?

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

#682

Post by adastra22 »

krainboltgreene wrote: post #648
adastra22 wrote: post #556

Earlier quoted context omitted.

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.

You have no idea if I remember with pixel perfect accuracy (whatever that even means). There are plenty of people with photographic memory. Also, you're a programmer you have no foundation of knowledge on which to make that assessment. You might as well opine on quarks or martian cellular life. My god the arrogance of people in my industry.

Repeated studies have shown that perfect "photographic memory" does not in fact exist. Nobody has it. Some people think that they do though, but when tested under lab conditions those claims don't hold up.

I don't believe these people are lying. They are self-reporting their own experiences, which unfortunately have the annoying property of being generated by the very mind that is living the experience.

What does it mean to have an eidetic memory? It means that when you remember something you vividly remember details, and can examine those details to your heart's content. When you do so, it feels like all those details are correct. (Or so I'm told, I'm the opposite with aphantasia.)

But it turns out if you actually have a photo reference and do a blind comparison test, people who report photographic memories actually don't do statistically any better than others in remembering specific fine details, even though they claim that they clearly remember.

The simpler explanation is that while all of our brains are provide hallucinated detail to fill the gaps of memories, their brains are wired up to present those made up details feel much more real than they do to others. That is all.

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

#683

Post by gdudeman »

i_have_an_idea wrote: post #377
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…

This sounds like the programmer equivalent of astrology. > Build context for the work you're doing. Put lots of your codebase into the context window. If you don’t say that, what do you think happens as the agent works on your codebase.

You don't say that - you instruct the LLM to read files about X, Y, and Z. Putting the context in helps the agent plan better (next step) and write correct code (final step).

If you're asking the agent to do chunks of work, this will get better results than asking it to blindly go forth and do work. Anthropic's best practices guide says as much.

If you're asking the agent to create one method that accomplishes X, this isn't useful.

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

#684

Post by HarHarVeryFunny »

adastra22 wrote: post #682
krainboltgreene wrote: post #648

Earlier quoted context omitted.

You have no idea if I remember with pixel perfect accuracy (whatever that even means). There are plenty of people with photographic memory. Also, you're a programmer you have no foundation of knowledge on which to make that assessment. You might as well opine on quarks or martian cellular life. My god the arrogance of people in my industry.

Repeated studies have shown that perfect "photographic memory" does not in fact exist. Nobody has it. Some people think that they do though, but when tested under lab conditions those claims don't hold up. I don't believe these people are lying. They are self-reporting their own experiences, which unfortunately have the annoying property of being generated by the very mind that is living the experience. What does it…

> Repeated studies have shown that perfect "photographic memory" does not in fact exist.

This may change your mind!

https://www.youtube.com/watch?v=jVqRT_kCOLI

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

#685

Post by sorhaindop »

benterix wrote: post #29
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…

> 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.

This exact phrase has been said by 3 different users... weird.

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

#686

Post by sorhaindop »

sorhaindop wrote: post #685
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.

This exact phrase has been said by 3 different users... weird.

"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" - smells like BS to me.

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

#687

Post by scotty79 »

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 use a cheaper model to compose a relevant context for the more expensive one?

Even better, use expensive model to create a general set of guidelines for picking the right context for your project, that the cheaper model will use in the future to pick the right context.

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

#688

Post by adastra22 »

HarHarVeryFunny wrote: post #684
adastra22 wrote: post #682

Earlier quoted context omitted.

Repeated studies have shown that perfect "photographic memory" does not in fact exist. Nobody has it. Some people think that they do though, but when tested under lab conditions those claims don't hold up. I don't believe these people are lying. They are self-reporting their own experiences, which unfortunately have the annoying property of being generated by the very mind that is living the experience. What does it…

> Repeated studies have shown that perfect "photographic memory" does not in fact exist. This may change your mind! https://www.youtube.com/watch?v=jVqRT_kCOLI

No, a YouTube video won’t convince me over repeated, verified lab experiments.

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

#689

Post by MangoCoffee »

dfedbeef wrote: post #639
MangoCoffee wrote: post #397

Earlier quoted context omitted.

At the end of the day, all tools are made to make their users' lives easier. I use GitHub Copilot. I recently did a vibe code hobby project for a command line tool that can display my computer's IP, hard drive, hard drive space, CPU, etc. GPT 4.1 did coding and Claude did the bug fixing. The code it wrote worked, and I even asked it to create a PowerShell script to build the project for release

Try typing ctrl+shift+escape.

LOL. I just want to try out vibe coding on something small with a persona based appoarch described here: https://humanwhocodes.com/blog/2025/06/persona-based-approac...

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

#690

Post by HarHarVeryFunny »

adastra22 wrote: post #688
HarHarVeryFunny wrote: post #684

Earlier quoted context omitted.

> Repeated studies have shown that perfect "photographic memory" does not in fact exist. This may change your mind! https://www.youtube.com/watch?v=jVqRT_kCOLI

No, a YouTube video won’t convince me over repeated, verified lab experiments.

So what do you make of the video - do you think it's fake, or are you just making the distinction between eidetic memory and photographic memory?

There are so many well documented cases of idiot savants with insane memory skills in various areas (books, music, dates/events, etc), that this type of snapshot visual memory (whatever you want to call it) doesn't seem surprising in that context - it'd really be a bit odd such diverse memory skills excluded one sensory modality (and it seems it doesn't).

Post reply on HN