Implicated

July 27th

So your argument is now RNG plays a bigger role so eventually they'll score a win by luck?

Uh, no. His argument is that the ~10% or so superiority you're fighting so hard to claim is no longer enough to have dominate sway over the overall outcome. Other factors, not random.

It's similar in that it also pins you at xhigh effort _combined_ with the workflows (which one might say isn't far off from proactive use of agents)

Just throwing it out there I've got an AX162-R (48c EPYC) with 128GB additional memory (384GB DDR5 total) that's been running a side project of mine for a year or so... I could be talked into moving that project if someone had a need for the hardware.

I'm chime in here as another Pi user, starting with OMP and then just ditching it for vanilla Pi + MCP/LSP from OMP as well as pi-cursor-sdk to get access to Composer 2.5 through Pi. I use this as my 'fast' research & report (through my project/codebase) or boilerplate/tightly-specced implementation agent that's available to my planning/orchestrator (GPT 5.5 if complex backend work, Fable/Opus if wanting the extended context or view/design heavy work).

Pi has been great in this role, as well as occasional use not as a sub-agent but by my own human hands when I want to interact with the Composer 2.5 model directly... which I do much less these days as I just use Codex 5.5 /fast. Pi's great though.

Just as a note to CC fans/users here since I had an opportunity to do so... I tested resuming a session that was stale at 950k tokens after returning from a full day or so of being idle, thus a fully empty quota/session.

Resuming it cost 5% of the current session and 1% of the weekly session on a max subscription.

But.. that doesn't solve the problem of having no indication in-session when it'll lose the cache. A nudge to /clear does nothing to indicate "or else face significant cost" nor does it indicate "your cache is stale".

Love the product. <3

At $400 a pop that’s $400,000,000-$4,000,000,000. A lot to throw at a single attack when you don’t actually know what defenses are in place.

Have you seen the price tag on some of the US jets? Are they not doing just this?

Uh, it sounds like you're having trouble understanding that people in this thread are talking about two wildly different "claude code" applications. Those who are claiming the resources issues don't apply to them are referring to the cli application, ie: `claude` and those are saying things like "Just open both apps..." are surely referring to their GUI versions.

lmao - I'm not at all proud of what you called an accomplishment. I literally said it _is_ amateur hour, it's hacked together, not safe, not stylish, not well engineered. But it does work. And despite your assumption about me learning anything - I had _no idea_ how generators worked. The realization that spinning an electric motor would result in electricity being produced blew my mind and got me asking claude things related to that, then I wanted to interface a wheel against my wheel to spin a stepper motor to get a charge and had the hair brain idea to just make the whole thing the generator instead. None of this was stuff I knew.

Despite this thing I made being rather useless in the grand scheme of things it was _wildly_ illuminating in terms of my understanding of electricity and the various objects around me and how they function. Which has spurred another rabbit hole that is having _real measurable effect_ for a host of feral cats to live a more comfortable life. (Not the wheel generator thing)

a machine told you what to do and you did it, like coloring by numbers - it doesn't make you an artist.

I never claimed to be an artist ;) And, maybe it's different for you, but someone or something showing me how to do something is quite literally the best way for me to learn. /shrug

I have to doubt that. If you were all those things, you would have been able to complete that project with very little effort, and without a machine telling you what to do.

I love that for you.

This

I've had very consistent success with plan mode, but when I haven't I've noticed many times it's been working with code/features/things that aren't well defined. ie: not using a well defined design pattern, maybe some variability in the application on how something could be done - these are the things I notice it really trips up on. Well defined interfaces, or even specifically telling it to identify and apply design principles where it seems logical.

When I've had repeated issues with a feature/task on existing code often times it really helps to first have the model analyze the code and recommend 'optimizations' - whether or not you agree/accept, it'll give you some insight on the approach it _wants_ to take. Adjust from there.

Oracles have their use too, but as long as you keep confusing "oracle" and "tool" you will get nowhere.

Arguably, I'm getting somewhere.. ;)

Right - it's not a big deal and it LITERALLY is amateur hour. But I did it. I wouldn't have done it prior, sure I could have done a bunch of google searches but the time investment it would have taken to sift through all that information and distill it into actionable chunks would have far exceeded the benefit of doing so, in this case.

The whole point is that it is amateur hour and it's wildly effective as a learning tool.

The fact it derived everything from things that have been done... yea, that's also the point? What point are you trying to make here? I'm well aware it's not a great tool if you're trying to use it to create novel things... but I'm not a nuclear physicist. I'm a builder, fixer, tinkerer who happens to make a living writing code. I use it to teach me how to do things, I use it to analyze problems and recommend approaches that I can then delve into myself.

I'm not asking it to fold proteins. (I guess that's been done quite a bit too, so would be amateur as well)

Thank you.

Can you not? If not, learn how to. You'll find it helps immensely.

You didn't use plan mode.

If I was on the "replace all the meatsacks AGI ftw" team then I would have referred to it as an oracle, by your own logic, wouldn't I have?

It's a tool. It's good for some things, not for others. Use the right tool for the job and know the job well enough to know which tools apply to which tasks.

More than anything it's a learning tool. It's also wildly effective at writing code, too. But, man... the things that it makes available to the curious mind are rather unreal.

I used it to help me turn a cat exercise wheel (think huge hamster wheel) into a generator that produces enough power to charge a battery that powers an ESP32 powered "CYD" touchscreen LCD that also utilizes a hall effect sensor to monitor, log and display the RPMs and "speed" (given we know the wheel circumference) in real time as well as historically.

I didn't know anything about all this stuff before I started. I didn't AGI myself here. I used a learning tool.

But keep up with your schtick if that's what you want to do.

So, you observed some telemetry - which would have been some sort of specific metric, right? Wouldn't you communicate that to them as well, not just "it's slow"?

"Hey, I saw that metric A was reporting 40% slower, are you aware already or have any ideas as to what might be causing that?"

Those two approaches are going to produce rather distinctly different results whether you're speaking to a human or typing to a GPU.

Well now I look like an idiot. But I did learn some things! :D My apologies.

Typically the uncountable version is used with a measure of quantity, while the countable version denotes different kinds (flours - different types of flour; peoples - different groups of people).

This was very helpful, thank you! (I had just gotten off the phone with Claude learning about countable and uncountable nouns but those additional details you provided should prove quite valuable)

I got curious and had to fire up the ol LLM to find out what the story is about the words that aren't pluralized - TIL about countable and uncountable nouns. I wonder if the guy giving you trouble about your English speaks French.

You'll find, at times, that those communicating in a language that's not their primary language will tend to deviate from what one whose it was their primary language might expect.

If that's obvious to you than you're just being rude. If it's not obvious to you, then you'll also find this is a common deviance (plural 'code') from those who come from a particular primary language's region.

Edit; This got me thinking - what is the grammar/rule around what gets pluralized and what doesn't? How does one know that "code" can refer to a single line of code, a whole file of code, a project, or even the entirety of all code your eyes have ever seen without having to have an s tacked on to the end of it?

You're holding it wrong.

Set the boundaries and guidelines before it starts working. Don't leave it space to do things you don't understand.

ie: enforce conventions, set specific and measurable/verifiable goals, define skeletons of the resulting solutions if you want/can.

To give an example. I do a lot of image similarity stuff and I wanted to test the Redis VectorSet stuff when it was still in beta and the PHP extension for redis (the fastest one, which is written in C and is a proper language extension not a runtime lib) didn't support the new commands. I cloned the repo, fired up claude code and pointed it to a local copy of the Redis VectorSet documentation I put in the directory root telling it I wanted it to update the extension to provide support for the new commands I would want/need to handle VectorSets. This was, idk, maybe a year ago. So not even Opus. It nailed it. But I chickened out about pushing that into a production environment, so I then told it to just write me a PHP run time client that mirrors the functionality of Predis (pure-php implementation of redis client) but does so via shell commands executed by php (lmao, I know).

Define the boundaries, give it guard rails, use design patterns and examples (where possible) that can be used as reference.

Not trying to be snarky, with all due respect... this is a skill issue.

It's a tool. It's a wildly effective and capable tool. I don't know how or why I have such a wildly different experience than so many that describe their experiences in a similar manner... but... nearly every time I come to the same conclusion that the input determines the output.

If they implement something with a not-so-great approach, they'll keep adding workarounds or redundant code every time they run into limitations later.

Yes, when the prompt/instructions are overly broad and there's no set of guardrails or guidelines that indicate how things should be done... this will happen. If you're not using planning mode, skill issue. You have to get all this stuff wrapped up and sorted before the implementation begins. If the implementation ends up being done in a "not-so-great" approach - that's on you.

If you tell them the code is slow

Whew. Ok. You don't tell it the code is slow. Do you tell your coworker "Hey, your code is slow" and expect great results? You ask it to benchmark the code and then you ask it how it might be optimized. Then you discuss those options with it (this is where you do the part from the previous paragraph, where you direct the approach so it doesn't do "no-so-great approach") until you get to a point where you like the approach and the model has shown it understands what's going on.

Then you accept the plan and let the model start work. At this point you should have essentially directed the approach and ensured that it's not doing anything stupid. It will then just execute, it'll stay within the parameters/bounds of the plan you established (unless you take it off the rails with a bunch of open ended feedback like telling it that it's buggy instead of being specific about bugs and how you expect them to be resolved).

you can have 10 bespoke tests for every bug. Plus a new mocking framework created every time the last one turns out to be unfit for purpose.

This is an area I will agree that the models are wildly inept. Someone needs to study what it is about tests and testing environments and mocking things that just makes these things go off the rails. The solution to this is the same as the solution to the issue of it keeping digging or chasing it's tail in circles... Early in the prompt/conversation/message that sets the approach/intent/task you state your expectations for the final result. Define the output early, then describe/provide context/etc. The earlier in the prompt/conversation the "requirements" are set the more sticky they'll be.

And this is exactly the same for the tests. Either write your own tests and have the models build the feature from the test or have the model build the tests first as part of the planned output and then fill in the functionality from the pre-defined test. Be very specific about how your testing system/environment is setup and any time you run into an issue testing related have the model make a note about that and the solution in a TESTING.md document. In your AGENTS.md or CLAUDE.md or whatever indicate that if the model is working with tests it should refer to the TESTING.md document for notes about the testing setup.

Personally, I focus on the functionality, get things integrated and working to the point I'm ready to push it to a staging or production (yolo) environment and _then_ have the model analyze that working system/solution/feature/whatever and write tests. Generally my notes on the testing environment to the model are something along the lines of a paragraph describing the basic testing flow/process/framework in use and how I'd like things to work.

The more you stick to convention the better off you'll be. And use planning mode.

Same, I still use CC mainly due to it being so wildly better at compaction. The overall experience of using OpenCode was far superior - especially with the LSP configured.

but for entirely non-technical reasons we had to exclude it

Able/willing to expand on this at all? Just curious.

On the native interface(s), surely, you can't.

I think you're missing his point entirely. The problem with these retail purifiers is that you either get quiet or effective. You don't get both.

Sure, you can't hear it from 10ft away - but how much air is it moving at that setting?

I have various configurations of these PC fan setups and the Arctic P14 Pro that you can get 5 for $32 on amazon are honestly wildly effective and designed for applications with some static pressure (radiators and such).

So we're back to; effective or quiet, you're only going to get both with the PC fans, for now.

I've been down this rabbit hole for a while now and sadly can't seem to find the article about the filtrete vs others, but there's been some people who tested the 'load' on these furnace filters and the Filtrete filters far exceeded everyone else in terms of airflow as the filters loaded up.

Re: Filter costs - stock up when costco has them on sale, which seems like every few months. They've got Filtrete 2500 (merv 14) for 3 filters for ~$35 if I remember correctly. I use them in my CR boxes and those I built for family (which I give them with a 3 pack of new filters and also instruct them to refill during costco sales)

I built one for a local stray cat rescue where it literally sits in the middle of the living space for 10+ cats, it's 4 months now since they started using it and the filters look quite dirty but the air flow is surprisingly still very good. (4x Noctua NF-F12 iPPC 3000 fans and 4x 16"x25"x1" Filtrete 2500 filters)

Here's some info re: which merv levels work best with various fan combinations (looks like if you're going to go with higher merv you'll need the static pressure to be able to continue to pull through them with any reasonable airflow once they're getting loaded up with stuff) - https://www.cleanairkits.com/blogs/news/what-happens-to-cadr...