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

341–350 of 706 posts

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

#341

Post by stuartjohnson12 »

ants_everywhere wrote: post #322
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…

> I really desperately need LLMs to maintain extremely effective context The context is in the repo. An LLM will never have the context you need to solve all problems. Large enough repos don't fit on a single machine. There's a tradeoff just like in humans where getting a specific task done requires removing distractions. A context window that contains everything makes focus harder. For a long time context windows we…

> An LLM will never have the context you need to solve all problems.

How often do you need more than 10 million tokens to answer your query?

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

#342

Post by taberiand »

jeremywho wrote: post #320
not_that_d wrote: post #304

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 goo…

My workflow is to use Claude desktop with the filesystem mcp server. I give claude the full path to a couple of relevant files related to the task at hand, ie where the new code should hook into or where the current problem is. Then I ask it to solve the task. Claude will read the files, determine what should be done and it will edit/add relevant files. There's typically a couple of build errors I will paste back in…

I've been using it the same way. One approach that's worked well for me is to start a project and first ask it to analyse and make a plan with phases for what needs to be done, save that plan into the project, then get it to do each phase in sequence. Once it completes a phase, have it review the code to confirm if the phase is complete. Each phase of work and review is a new chat.

This way helps ensure it works on manageable amounts of code at a time and doesn't overload its context, but also keeps the bigger picture and goal in sight.

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

#343

Post by fpauser »

risyachka wrote: post #321
not_that_d wrote: post #304

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 goo…

Pretty much my experience too. I usually go to option 2 - just write it by myself as it is same time-wise but keeps skills sharp.

Not to degenerate is really challenging these days. There are the bubbles that simulate multiple realities to us and try to untrain us logic thinking. And there are the llms that try to convice us that self thinking is unproductive. I wonder when this digitalophily suddenly turns into digitalophobia.

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

#345

Post by jiggawatts »

not_that_d wrote: post #304

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 goo…

Something I’ve discovered is that it may be worthwhile writing the prompt anyway, even for a framework you’re an expert with. Sometimes the AIs will surprise me with a novel approach, but the real value is that the prompt makes for excellent documentation of the requirements! It’s a much better starting point for doc-comments or PR blurbs than after-the-fact ramblings.

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

#347

Post by fpauser »

fwip wrote: post #186
markb139 wrote: post #175

I’ve tried 2 AI tools recently. Neither could produce the correct code to calculate the CPU temperature on a Raspberry Pi RP2040. The code worked, looked ok and even produced reasonable looking results - until I put a finger on the chip and thus raised the temp. The calculated temperature went down. As an aside the free version of chatGPT didn’t know about anything newer than 2023 so couldn’t tell me about the RP2350

I don't think a larger context window would help with that.

Best comment ;)

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

#348

Post by onion2k »

ants_everywhere wrote: post #322
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…

> I really desperately need LLMs to maintain extremely effective context The context is in the repo. An LLM will never have the context you need to solve all problems. Large enough repos don't fit on a single machine. There's a tradeoff just like in humans where getting a specific task done requires removing distractions. A context window that contains everything makes focus harder. For a long time context windows we…

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.

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

#349

Post by sdesol »

ants_everywhere wrote: post #322
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…

> I really desperately need LLMs to maintain extremely effective context The context is in the repo. An LLM will never have the context you need to solve all problems. Large enough repos don't fit on a single machine. There's a tradeoff just like in humans where getting a specific task done requires removing distractions. A context window that contains everything makes focus harder. For a long time context windows we…

> But they have to get better at understanding the repo by asking the right questions.

How I am tackling this problem is making it dead simple for users to create analyzers that are designed to enriched text data. You can read more about how it would be used in a search at https://github.com/gitsense/chat/blob/main/packages/chat/wid...

The basic idea is, users would construct analyzers with the help of LLMs to extract the proper metadata that can be semantically searched. So when the user does an AI Assisted search with my tool, I would load all the analyzers (description and schema) into the system prompt and the LLM can determine which analyzers can be used to answer the question.

A very simplistic analyzer would be to make it easy to identify backend and frontend code so you can just use the command `!ask find all frontend files` and the LLM will construct a deterministic search that knows to match for frontend files.

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

#350

Post by nwatson »

jeremywho wrote: post #320
not_that_d wrote: post #304

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 goo…

My workflow is to use Claude desktop with the filesystem mcp server. I give claude the full path to a couple of relevant files related to the task at hand, ie where the new code should hook into or where the current problem is. Then I ask it to solve the task. Claude will read the files, determine what should be done and it will edit/add relevant files. There's typically a couple of build errors I will paste back in…

One can also integrate with, say, a running PyCharm with the Jetbrains IDE MCP server. Claude Desktop can then interact directly with PyCharm.
Post reply on HN