Hacker News

Yeah this is the simpler and also effective strategy. A lot of people are building sophisticated AST RAG models. But you really just need to ask Claude to generally build a semantic index for each large-ish piece of code and re-use it when getting context.

You have to make sure the semantic summary takes up significantly less tokens than just reading the code or its just a waste of token/time.

Then have a skill that uses git version logs to perform lazy summary cache when needed.

Yeah we all converge to the same workflow, in my ai coding agent I'm working on now, I've added an "index" tool that uses tree-sitter to compress and show the AI a skeleton of a code file.

Here's the implementation for the interested: https://github.com/tontinton/maki/blob/main/maki-code-index%...

It seems like a very good use of LLMs. You should write a blog post with detail of your process with examples for people who are not into all AI tools as much. I only use Web UI. Lots of what you are saying is beyond me, but it does sound like clever strategy.

I think you've kind of hit on the more successful point here, which is that you should be keeping things focused in a sufficiently focused area to have better success and not necessarily needing more context.

This is really interesting; ive done very high level code maps but the entire project seems wild, it works?

So, small model figures out which files to use based on the code map, and then enriches with snippets, so big model ideally gets preloaded with relevant context / snippets up front?

Where does code map live? Is it one big file?

Your code map compresses signal on the context side. Same principle applies on the prompt side: prompts that front-load specifics (file, error, expected behavior) resolve in 1-2 turns. Vague ones spiral into 5-6. 1M context doesn't change that — it just gives you more room for the spiral.

whenever I see post like this

i said well yeah, but its too sophiscated to be practical

very interested in this approach and many other people are for sure. Please do a blog post.

1M context is super useful with Gemini, not so much for coding, but for data analysis.

If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context.

I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong

I think context decay is a bigger problem then we feel like.

Is it ever useful to have a context window that full? I try to keep usage under 40%, or about 80k tokens, to avoid what Dex Horthy calls the dumb zone in his research-plan-implement approach. Works well for me so far.

No vibes allowed: https://youtu.be/rmvDxxNubIg?is=adMmmKdVxraYO2yQ

I've been using the 1M window at work through our enterprise plan as I'm beginning to adopt AI in my development workflow (via Cline). It seems to have been holding up pretty well until about 700k+. Sometimes it would continue to do okay past that, sometimes it started getting a bit dumb around there.

(Note that I'm using it in more of a hands-on pair-programming mode, and not in a fully-automated vibecoding mode.)

So a picture is worth 1,666 words?

The quality with the 1M window has been very poor for me, specifically for coding tasks. It constantly forgets stuff that has happened in the existing conversation. n=1, ymmv

Well, the question is what is contributing to the usage. Because as the context grows, the amount of input tokens are increasing. A model call with 800K token as input is 8 times more expensive than a model call with 100K tokens as input. Especially if we resume a conversation and caching does not hit, it would be very expensive with API pricing.

This might burn through usage faster too though.

yeah it totally does not remain coherent past 200k, would have been too nice.

As someone who did Python professionally from a software engineering perspective, I've actually found Python to be pretty crappy really: unaware of _good_ idioms living outside tutorials and likely 90% of Python code out there that was simply hacked together quickly.

I have not tested, but I would expect more niche ecosystems like Rust or Haskell or Erlang to have better overall training set (developer who care about good engineering focus on them), and potentially produce the best output.

For C and C++, I'd expect similar situation with Python: while not as approachable, it is also being pushed on beginning software engineers, and the training data would naturally have plenty of bad code.

I've found it's ok at Rust. I think a lot of existing Rust code is high quality and also the stricter Rust compiler enforces that the output of the LLM is somewhat reasonable.

It is really good at writing C++ for Arduino, can one-shot most programs.

LLMsdo great with Rust though

I've had a similar experience as a graphics programmer that works in C++ every day

Writing quick python scripts works a lot better than niche domain specific code

nor web engineers (backend) that are not doing standard crud work.

I have seen these shine on frontend work

I think the combinatorial space is just too much. When I did web dev it was mostly transforming HTML/JSON from well-defined type A to well-defined type B. Everything is in text. There's nothing to reason about besides what is in the prompt itself. But constructing and maintaining a mental model of a chip and all of its instructions and all of the empirical data from profiling is just too much for SOTA to handle reliably.

What model(s) do you use with OpenCode? Can you use opus4.6 1m? Is it better in terms of usage if you use the same model?

> As you got closer to 100k performance degraded substantially

In practice, I haven't found this to be the case at all with Claude Code using Opus 4.6. So maybe it's another one of those things that used to be true, and now we all expect it to be true.

And of course when we expect something, we'll find it, so any mistakes at 150k context use get attributed to the context, while the same mistake at 50k gets attributed to the model.

Personally, even though performance up to 200k has improved a lot with 4.5 and 4.6, I still try to avoid getting up there — like I said in another comment, when I see context getting up to even 100k, I start making sure I have enough written to disk to type /new, pipe it the diff so far, and just say “keep going.” I feel like the dropoff starts around maybe 150k, but I could be completely wrong. I thought it was funny that the graph in the post starts at 256k, which convenient avoids showing the dropoff I'm talking about (if it's real).

I mentioned this at work but context still rots at the same rate. 90k tokens consumed has just as bad results in 100k context window or 1M.

Personally, I’m on a 6M+ line codebase and had no problems with the old window. I’m not sending it blindly into the codebase though like I do for small projects. Good prompts are necessary at scale.

The benchmark charts provided are the writeup. Everything else is just anecdata.

Isn't transformer attention quadratic in complexity in terms of context size? In order to achieve 1M token context I think these models have to be employing a lot of shortcuts.

I'm not an expert but maybe this explains context rot.

No change for Pro, just checked it, the 1M context is still extra usage.

I have Max 20x and they're still separate on 2.1.75.

Those sorts of volume discounts are what you do when you're trying to incentivize more consumption. Anthropic already has more demand then they're logistically able to serve, at the moment (look at their uptime chart, it's barely even 1 9 of reliability). For them, 1 user consuming 5 units of compute is less attractive than 5 users consuming 1 unit.

They would probably implement _diminishing_-value pricing if pure pricing efficiency was their only concern.

It is not the plan they want you to buy. It is a pricing strategy to get you to buy the 20x plan.

I think they are both subsidized so either is a great deal.

Yeah the free lunch on tokens is almost over. Get them while they’re still cheap

5 times the already subsidised rate is still a discount.

We’ll make it up on volume.

5 for 5

I wish I had this kind of experience. I threw a tedious but straightforward task at Claude Code using Opus 4.6 late last week: find the places in a React code base where we were using useState and useEffect to calculate a value that was purely dependent on the inputs to useEffect, and replace them with useMemo. I told it to be careful to only replace cases where the change did not introduce any behavior changes, and I put it in plan mode first.

It gave me an impressive plan of attack, including a reasonable way to determine which code it could safely modify. I told it to start with just a few files and let me review; its changes looked good. So I told it to proceed with the rest of the code.

It made hundreds of changes, as expected (big code base). And most of them were correct! Except the places where it decided to do things like put its "const x = useMemo(...)" call after some piece of code that used the value of "x", meaning I now had a bunch of undefined variable references. There were some other missteps too.

I tried to convince it to fix the places where it had messed up, but it quickly started wanting to make larger structural changes (extracting code into helper functions, etc.) rather than just moving the offending code a few lines higher in the source file. Eventually I gave up trying to steer it and, with the help of another dev on my team, fixed up all the broken code by hand.

It probably still saved time compared to making all the changes myself. But it was way more frustrating.

What kinds of things are you building? This is not my experience at all.

Just today I asked Claude using opus 4.6 to build out a test harness for a new dynamic database diff tool. Everything seemed to be fine but it built a test suite for an existing diff tool. It set everything up in the new directory, but it was actually testing code and logic from a preexisting directory despite the plan being correct before I told it to execute.

I started over and wrote out a few skeleton functions myself then asked it write tests for those to test for some new functionality. Then my plan was to the ask it to add that functionality using the tests as guardrails.

Well the tests didn’t actually call any of the functions under test. They just directly implemented the logic I asked for in the tests.

After $50 and 2 hours I finally got something working only to realize that instead of creating a new pg database to test against, it found a dev database I had lying around and started adding tables to it.

When I managed to fix that, it decided that it needed to rebuild multiple docker components before each test and test them down after each one.

After about 4 hours and $75, I managed to get something working that was probably more code than I would have written in 4 hours, but I think it was probably worse than what I would have come up with on my own. And I really have no idea if it works because the day was over and I didn’t have the energy left to review it all.

We’ve recently been tasked at work with spending more money on Claude (not being more productive the metric is literally spending more money) and everyone is struggling to do anything like what the posts on HN say they are doing. So far no one in my org in a very large tech company has managed to do anything very impressive with Claude other than bringing down prod 2 days ago.

Yes I’m using planning mode and clearing context and being specific with requirements and starting new sessions, and every other piece of advice I’ve read.

I’ve had much more luck using opus 4.6 in vs studio to make more targeted changes, explain things, debug etc… Claude seems too hard to wrangle and it isn’t good enough for you to be operating that far removed from the code.

I find that Opus misses a lot of details in the code base when I want it to design a feature or something. It jumps to a basic solution which is actually good but might affect something elsewhere.

GPT 5.4 on codex cli has been much more reliable for me lately. I used to have opus write and codex review, I now to the opposite (I actually have codex write and both review in parallel).

So on the latest models for my use case gpt > opus but these change all the time.

Edit: also the harness is shit. Claude code has been slow, weird and a resource hog. Refuses to read now standardized .agents dirs so I need symlink gymnastics. Hides as much info as it can… Codex cli is working much better lately.

Im convinced everyone saying this is building the simplest web apps, and doing magic tricks on themselves.

My experience is that it gets you 80-90% of the way at 20x the speed, but coaxing it into fixing the remaining 10-20% happens at a staggeringly slow speed.

All programming is like this to some extent, but Claude's 80/20 behavior is so much more extreme. It can almost build anything in 15-30 minutes, but after those 15-30 minutes are up, it's only "almost built". Then you need to spend hours, days, maybe even weeks getting past the "almost".

Big part of why everyone seems to be vibe coding apps, but almost nobody seems to be shipping anything.

I am starting to believe it’s not OPUS but developers getting better at using LLMs across the board. And not realizing they are just getting much better at using these tools.

I also thought it was OPUS 4.5 (also tested a lot with 4.6) and then in February switched to only using auto mode in the coding IDEs. They do not use OPUS (most of the times), and I’m ending up with a similar result after a very rough learning curve.

Now switching back to OPUS I notice that I get more out of it, but it’s no longer a huge difference. In a lot of cases OPUS is actually in the way after learning to prompt more effectively with cheaper models.

The big difference now is that I’m just paying 60-90$ month for 40-50hrs of weekly usage… while I was inching towards 1000$ with OPUS. I chose these auto modes because they don’t dig into usage based pricing or throttling which is a pretty sweet deal.

> PRD

Is it Baader-Meinhof or is everyone on HN suddenly using obscure acronyms?

> It was also the first AI I felt, "Damn, this thing is smarter than me."

1000% agree. It's also easy to talk to it about something you're not sure it said and derive a better, more elegant solution with simple questioning.

Gemini 3.1 also gives me these vibes.

I've seen a few instances of where Claude showed me a better way to do something and many many more instances of where it fails miserably.

Super simple problem :

I had a ZMK keyboard layout definition I wanted it to convert it to QMK for a different keyboard that had one key less so it just had to trim one outer key. It took like 45 minutes of back and forth to get it right - I could have done it in 30 min manually tops with looking up docs for everything.

Capability isn't the impressive part it's the tenacity/endurance.

I had been able to get it into the classic AI loop once.

It was about a problem with calculation around filling a topographical water basin with sedimentation where calculation is discrete (e.g. turn based) and that edge case where both water and sediments would overflow the basin; To make the matter simple, fact was A, B, C, and it oscillated between explanation 1 which refuted C, explanation 2 which refuted A and explanation 3 that refuted B.

I'll give it to opus training stability that my 3 tries using it all consistently got into this loop, so I decided to directly order it to do a brute force solution that avoided (but didn't solve) this problem.

I did feel like with a human, there's no way that those 3 loop would happen by the second time. Or at least the majority of us. But there is just no way to get through to opus 4.6

Opus 4.6 is AGI in my book. They won’t admit it, but it’s absolutely true. It shows initiative in not only getting things right but also adding improvements that the original prompt didn't request that match the goals of the job.

> [...] with multiple agents working at the same time, each at that speed.

Horizontal parallelising of tasks doesn't really require any modern tech.

But I agree that Opus 4.6 with 1M context window is really good at lots of routine programming tasks.

Opus-4.6 is so far ahead of the rest that I think Anthropic is the winner in winner-take-all

It's so far the best model that answers my questions about Wolfram language.

That being said it's the only use case for me. I won't subscribe to something that I can't use with third party harness.

I have a PhD in a niche field and this can do my job ;)

Not sure if this means I should get a more interesting job or if we are all going to be at the mercy of UBI eventually.

It’s still pretty poor writing powershell

I had Opus 4.6 running on a backend bug for hours. It got nowhere. Turned out the problem was in AWS X-ray swizzling the fetch method and not handling the same argument types as the original, which led to cryptic errors.

I had Opus 4.6 tell me I was "seeing things wrong" when I tried to have it correct some graphical issues. It got stuck in a loop of re-introducing the same bug every hour or so in an attempt to fix the issue.

I'm not disagreeing with your experience, but in my experience it is largely the same as what I had with Opus 4.5 / Codex / etc.

But does it still generate slop?

I'm late to the party and I'm just getting started with Antrophic models. I have been finding Sonnet decent enough, but it seems to have trouble naming variables correctly (it's not just that most names are poor and undescriptive, sometimes it names it wrong, confusing) or sometimes unnecessarily declaring, re-declaring variables, encoding, decoding, rather than using the value that's already there etc. Is Opus better at this?

Just yesterday I asked it to repeat a very simple task 10 times. It ended up doing it 15 times. It wasn't a problem per se, just a bit jarring that it was unable to follow such simple instructions (it even repeated my desire for 10 repetitions at the start!).

I’ll put out a suggestion you pair with codex or deepthink for audit and review - opus is still prone to … enthusiastic architectural decisions. I promise you will be at least thankful and at most like ‘wtf?’ at some audit outputs.

Also shout out to beads - I highly recommend you pair it with beads from yegge: opus can lay out a large project with beads, and keep track of what to do next and churn through the list beautifully with a little help.

Bullshit.

The replies to this really make me think that some people are getting left behind the AI age. Colleges are likely already teaching how to prompt, but a lot of existing software devs just don't get it. I encourage people who aren't having success with AI to watch some youtube videos on best practices.

The multi-agent angle is interesting from a cost perspective. At Opus 4.6 pricing ($15/MTok input, $75/MTok output), running several concurrent agents on 1M context sessions gets expensive fast — but the math still works if you're replacing hours of senior engineer time.

The shift I've noticed: 1M context makes "load the whole codebase once, run many agents" viable, whereas before you were constantly re-chunking and losing context. The per-task cost goes up but the time-to-correct-output drops significantly.

The harder problem for most teams is routing — knowing which tasks actually need Opus at 1M vs. Sonnet at 200k. Opus 4.6 at 1M is overkill for 80% of coding tasks. The ROI only works if you're being intentional about when to use it.

Spot on. That cliff might be less about the model failing at distance and more about noise accumulating faster than signal. In prod, most of what fills the window is file reads, grep output, and tool overhead, i.e., low-value tokens. By 700k you're not really testing long-context reasoning, you're testing the model's ability to find signal in a haystack it built itself.

Did it get better? I used sonnet 4.5 1m frequently and my impression was that it was around the same performance but a hell of a lot faster since the 1m model was willing to spends more tokens at each step vs preferring more token-cautious tool calls.

Random: are you personally paying for Claude Code or is it paid by you employer?

My employer only pays for GitHub copilot extension

That's correct. Input caching helps, but even then at e.g. 800k tokens with all of them cached, the API price is $0.50 * 0.8 = $0.40 per request, which adds up really fast. A "request" can be e.g. a single tool call response, so you can easily end up making many $0.40 requests per minute.

If you use context cacheing, it saves quite a lot on the costs/budgets. You can cache 900k tokens if you want.

Yeah, morning eastern time Claude is brutal.

That game is AWESOME! The fact that was vibe coded is insane.

Out of curiosity, what specific use cases on programmatic SEO are you currently doing with Opus?

I don't think they're claiming "no degradation at scale", are they? They still report a 91.9->78.3 drop. That's just a better drop than everyone else (is the claim).

Same. First time in 2 months that I found it easier to fix the bugs it created manually, rather than get it to fix. Its google-code-CLI-on-gemini-2.5 level bad for me today. Meaning, almost comically bad.

Improves outputs relative to what? Compared to previous contexts of 1M, it improves outputs by allowing them to exist (because previously you couldn't exceed 200K). Compared to contexts of <200K, it degrades outputs rather than improves them, but that's what you'd expect from longer contexts. It's still better than compaction, which was previously the alternative.

Did u use the API or subscription?

rarely go over 25 percent in codex but i hit 80 on claude code in just a short time.

Yes, full context is used to generate each new token.

I’ve been using 1M for a while and it defers it and makes it worse almost when it happens. Compacting a context that big loses a ton of fidelity. But I’ve taken to just editing the context instead (double esc). I also am planning to build an agent to slice the session logs up into contextually useful and useless discarding the useless and keeping things high fidelity that way. (I.e., carve up with a script the jsonl and have subagent haiku return the relevant parts and reconstructing the jsonl)

It's almost certainly not quadratic at 1M. This would be wildly infeasible at scale. 10^6^2 = 10^12. That's a trillion things.

They are probably doing something like putting the original user prompt into the model's environment and providing special tools to the model, along with iterative execution, to fully process the entire context over multiple invokes.

I think the Recursive Language Model paper has a very good take on how this might go. I've seen really good outcomes in my local experimentation around this concept:

https://arxiv.org/abs/2512.24601

You can get exponential scaling with proper symbolic stack frames. Handling a gigabyte of context is feasible, assuming it fits the depth first search pattern.

They're probably taking shortcuts such as taking advantage of sparsity. There are various tricks like that mentioned in some papers, although the big companies are getting more and more secretive about how their models work so you won't necessarily find proof.

You can pin to specific models with —-model. Check out their doc. See https://support.claude.com/en/articles/11940350-claude-code-.... You can also pin to a less specific tag like sonnet-4.5[1m] (that’s from memory might be a little off).

Anthropic is famous for changing things under your feet. Claude code is basically alpha software with a global footprint.

I hear what you're saying, but for a lot of people coding isn't something we can throw 40+ hours per week at.

My main job is running a small eComm business, and I have to both develop software automations for the office (to improve productivity long-term) while also doing non-coding day to day tasks. On top of this, I maintain an open source project after hours. I've also got a young family with 3 kids.

I'm not saying Claude is the damn singularity or anything, but stuff is getting done now that simply wasn't being addressed before.

Not hard, but time consuming. In the past two weeks I've had Claude Code write me around 35k lines of code across 350 commits. It's a project which is giving positive impact to the company, but we would never have started it without CC as the effort would have been too big compared to the impact.

It's not that interesting.

You're witnessing the rise of the Developer Technician or Software Technician. They can get a machine to print out an application but you will still need an engineer to know how it works or to get it working. This used to be juniors learning to be senior devs/engineers. Now it is a split between technicians and engineers. The market will be up shit creek when all their technicians can't vibe code their way out of not understanding the code.

Only someone not using Claude could equate human coding.

I think this is just the nature of a nondeterministic system; occasionally you're gonna be unlucky enough to encounter the leftmost segment of the bell curve.

In my experience dumping a summary + starting a fresh session helps in these cases.

Unless you're clearing up the context for each description or processing them in parallel with subagents your context window will grow for each short description added to it making you hit those hour limits.

I find it hard to understand that people consider $200 p/m a lot for what they are getting. Expensive compared to what? A netflix sub?

A 1hr of a senior dev is at least $100, depending where one lives. Since Claude saves me hours every day, it pays for itself almost instantly. I think the economic value of the Claude subscription is on the order of $20-40k a month for a pro.

whats the need? you have the session in a file as a dag. you can summarize to a log whenever you want. doesnt need to be as it goes.

earlier today i actually spent a bit of time asking claude to make an mcp to introspect that - break the session down into summarized topics, so i could try dropping some out or replacing the detailed messages with a summary - the idea being to compact out a small chunk to save on context window, rather than getting it back to empty.

the file is just there though, you can run jq against it to get a list of writes, and get an agent to summarize

I imagine you can do this with a hook that fires every time claude stops responding:

https://code.claude.com/docs/en/hooks-guide

Backup your config and ask Claude. I’ve done this for all kinds of things like mcp and agent config.

use claude hooks - in .claude/settings.json you can have it run on different claude events like "PreToolUse" or "Stop" and in those events you pass in commands you want it to run.

You can have stuff like for the "stop" event, run foobar.sh and in foobar.sh do cool stuff like format your code, run tests, etc.

I think your instinct is right. More context isn't free, even when the window supports it, and the model still has to attend to everything in there, and noise dilutes the signal. A cleaner, smaller context consistently gives better outputs than a bloated one, regardless of window size. For sure, the 1M window is great for not having to compact mid-task. But "I can fit more" and "I should put more in" are very different things. At least in my mind.

No, because it's not a hello-world Electron/React "app".

There is compaction, which is analogous to gc