---

SYSTEM:

Got it. Those are the setup commands for Simon Willison's LLM CLI tool, which lets you interact with language models from the command line.

The -e flag installs it in editable mode, and [test] pulls in the test dependencies. Are you running into any issues with the installation or tests? What are you working on with the LLM library?

USER: Correct. You run them using your code tooling.

SYSTEM:

Realized inability to execute requested Python commands.The user is telling me to run these commands using my code tooling. They want me to actually execute this. Let me think about what tools I have available:

I have the repl tool which runs JavaScript code in a browser environment I have artifacts for creating code/documents I have web_search and web_fetch

The user wants me to:

Checkout https://github.com/simonw/llm Run pip install -e '.[test]' Run pytest

But I don't have a tool that can:

Clone git repositories Run shell commands like pip or pytest Execute Python code in a command-line environment

The repl tool is JavaScript-only and runs in a browser environment, not a server environment where I could run shell commands. I should clarify that I don't have the capability to run shell commands, install Python packages, or execute pytest. I can only run JavaScript code in a browser environment via the analysis tool. I need to be direct and clear about this limitation, following the user's preferences to eliminate filler and be straightforward.I don't have tooling that can run shell commands, clone git repos, install Python packages, or execute pytest. My only code execution environment is a JavaScript browser REPL. I can't run pip, pytest, or any command-line tools. I can only execute JavaScript code in a sandboxed browser environment. What were you hoping to accomplish? Do you need help understanding the test setup, or were you expecting different capabilities?R

For those who don't have time to dig into the gist, did it work and do a good job? I assume yes to at least nominally working or you would have mentioned that, but any other thoughts on the solution it produced?

But that prompt leads me to believe that you're going to get rather 'random' results due to leaving SO much room for interpretation.

Also, in my experience, punctuation is important - particularly for pacing and grouping of logical 'parts' of a task and your prompt reads like a run on sentence.

Making a lot of assumptions here - but I bet if I were in your shoes and looking to write a prompt to start a task of a similar type that my prompt would have been 5 to 20x the length of yours (depending on complexity and importance) with far more detail, including overlapping of descriptions of various tasks (ie; potentially describing the same thing more than once in different ways in context/relation to other things to establish relation/hierarchy).

I'm glad you got what you needed - but these types of prompts and approaches are why I believe so many people think these models aren't useful.

You get out of them what you put into them. If you give them structured and well written requirements as well as a codebase that utilizes patterns you're going to get back something relative to that. No different than a developer - if you gave a junior coder, or some team of developers the following as a feature requirement: `implement a fuzzy search for conversations and reports either when selecting "Go to Conversation" or "Go to Report" and typing the title or when the user types in the title in the main input field, and none of the standard elements match, a search starts with a 2s delay` then you can't really be mad when you don't get back exactly what you wanted.

edit: To put it another way - spend a few more minutes on the initial task/prompt/description of your needs and you're likely to get back more of what you're expecting.

And I actually like Claude more because of that.

codex will indeed work more independently but you will have hard time when it isn't what you want. It will use python script just to do simple edits in files ( niesearch and replace for unique code snippets in small files) when it's wrong good look convincing it (it already have some outdated info like on latest docker image releases and convincing it that Debian base changed was challenging) it uses context more effectively but it will lack explanation why it is doing what it is doing, asking it to explain will just cause it to do something else without any word.

and of course lack of proper permissions for running commands. sandbox is cool but I do not want it to be able to commit, I want it to just edit files or I want to have some more control over what it does.

you can run codex as mcp server, I prefer adding it to Claude and ask to do cooperative plan, codex will do great analysis and plan and I can comfortable work with Claude on the code that matches my style

[1] https://www.reddit.com/r/ClaudeAI/comments/1mgwohq/ultrathin...

1. Different LLMs require different prompts and information

2. They ignore LLMs non determinism, you should run the experiment several times

I will say, Claude does seem to need a verbose prompt. Often I'll write my prompts as tasks in Notion and have it pull then via MCP (which is nice, because it tracks and documents its work in the process). But once you've given it a few paragraphs about the why and how, my experience is that it's pretty self sufficient. Granted, I'm using Cursor and not CC; I don't know if that makes much of a difference.

Sticking with ChatGPT pro sub and gpt5 codex on high.

Sonnet on the other hand gets tripped up constantly due to the complexity. I'm not seeing the improvement I was hoping for with 4.5, and it's just given up on attempting to implement support for date-time functionality. Codex has nailed the same task, yet Anthropic claim OpenAI have the inferior product?

I'm pretty sad about this as I'm gunning for Anthropic and would have loved to see them at least match Codex with this new release. If OpenAI stays on this course then Claude Code is toast without an important breakthrough. It doesn't help that they're also the more expensive product and have service quality issues pushing people to quit the platform.

Claude Code on max plan is why I use Sonnet/Opus, but if ChatGPT pro includes codex usage I may switch.

Also, trying GPT-5-Codex

models themselves are deterministic, this is a huge pet peeve of mine, so excuse the tangent, but the appearance of nondeterminism comes from a few sources, but imho can be largely attributed to the probabilistic methods used to get appropriate context and enable timely responses. here's an example of what I mean, a 52-card deck. The deck order is fixed once you shuffle it. Drawing "at random" is a probabilistic procedure on top of that fixed state. We do not call the deck probabilistic. We call the draw probabilistic. Another exmaple, a pot of water heating on a stove. Its temperature follows deterministic physics. A cheap thermometer adds noisy, random error to each reading. We do not call the water probabilistic. We call the measurement probabilistic.

Theoretical physicists run into such problems, albeit far more complicated, and the concept for how they deal with them is called ergodicity. The models at the root of LLM's do exhibit ergodic behavior; the time average and the ensemble average of an observable are identical, i.e. the average response of a single model over a long duration and the average of many similar models at a fixed moment are equivalent.

https://github.com/sutt/innocuous/blob/master/docs/dev-summa...

Check it out, I'd be curious of your feedback.

Code is the only good thing about the tech industry. Everything else is capitalist hellscape shareholder dystopia. Thinking on it, its hilarious that any self-respecting coder is excited about these tools, because what you're excited for is a world where, now, at best, your entire job is managing unpredictable AI agents while sitting in meetings all day to figure out what to tell your AI agents to build. You don't get to build the product you want. You don't get to build it how you want. You'll be a middle manager that gets to orchestrate the arguments between the middle manager you already had and the inflexible computer.

You don't have to participate in a future you aren't interested in. The other day my boss asked me if I could throw Cursor at some task we've had backlogged for a while. I said "for sure my dude" then I just did it myself. It took me like four hours, and my boss was very impressed with how fast Cursor was able to do it, and how high quality the code was. He loves the Cursor metrics dashboard for "lines accepted" or whatever, every time he screenshares he has that tab open, so sometimes I task it on complicated nonsense tasks then just throw away the results. Seeing the numbers go up makes him happy, which makes my life easier, so its a win-win. Our CTO is really proud of "what percentage of our code is AI written" but I'm fairly certain that even the engineers who use it in earnest actually commit, like, 5% of what Cursor generates (and many do not use it in earnest).

The sentiment shift I've observed among friends and coworkers has been insane over the past two months. Literally no one cares about it anymore. The usage is still there, but its a lot more either my situation or just a "spray and pray" situation that creates a ton of disillusioned water cooler conversations.

If you allow your codebase to grow unfamiliar, even unrecognisable to you, that's on you, not the AI. Chasing some illusion of control via LLM output reproducibility won't fix the systemic problem of you integrating code that you do not understand.

While it's impressive that you can now just have an llm build this, I wouldn't be surprised if the result of these 30 hours is essentially just a re-hash of one of those example Slack clones. Especially since all of these models have internet access nowadays; I honestly think 30 hours isn't even that fast for something like this, where you can realistically follow a tutorial and have it done.

In fact, I just did a quick google search and found this 15 hour course about building a slack clone: https://www.codewithantonio.com/projects/slack-clone

it's going to be an issue I think, now that lots of these agents support computer use, we are at the point where you can install an app, tell the agent you want something that works exactly the same and just let it run until it produces it.

The software world may find it's got more in common with book authors than they thought sooner rather than later once full clones of popular apps are popping out of coding tools. It will be interesting to see if this results in a war of attrition with counter measures and strict ToU that prohibit use by AI agents etc.

Just to illustrate, say you are running on a slow machine that outputs 1 token per hour. At that speed you would produce approximately one sentence.

Imagine reviewing 30 hours of 2025-LLM code.

I've been worried about this for a while. I feel like Claude in particular took a step back in my own subjective performance evaluation in the switch from 3.7 to 4, while the benchmark scores leaped substantially.

To be fair, benchmarking has always been the most difficult problem to solve in this space, so it's not surprising that benchmark development isn't exactly keeping pace with all of the modeling/training development happening.

I’m not sure this is entirely what you’re driving at, but the example I always think of in my head is “I want an AI agent that will scan through my 20 to 30,000 photos, remove all the duplicates, then organize them all in some coherent fashion.” that’s the kind of service I need right now, and it feels like something AI should be able to do, yet I have not encountered anything that remotely accomplishes this task. I’m still using Dupe Guru and depending on the ref system to not scatter my stuff all over further.

Sidebar, if anybody has any recommendations for this, I would love to hear them lol

I don't understand why this kind of thing is useful. Do the thing yourself and move on. For every one problem like this, AI can do 10 better/faster than I can.

It also consistently gets into drama with the other agents e.g. the other day when I told it we were switching to claude code for executing changes, after badmouthing claude's entirely reasonable and measured analysis it went ahead and decided to `git reset --hard` even after I twice pushed back on that idea.

Whereas gemini and claude are excellent collaborators.

When I do decide to hail mary via GPT-5, I now refer to the other agents as "another agent". But honestly the whole thing has me entirely sketched out.

To be clear, I don't think this was intentionally encoded into GPT-5. What I really think is that OpenAI leadership simply squandered all its good energy and is now coming from behind. Its excellent talent either got demoralized or left.

Sometimes in between this variability of performance it pops up a little survey. "How's Claude doing this session from 1-5? 5 being great." and i suspect i'm in some experiment of extremely low performance. I'm actually at the point where i get the feeling peak hour weekdays is terrible and odd hour weekends are great even when forcing a specific model.

While there is some non-determinism it really does feel like performance is actually quite variable. It would make sense they scale up and down depending on utilization right? There was a post a week ago from Anthropic acknowledging terrible model performance in parts of August due to an experiemnt. Perhaps also at peak hour GPT has more datacenter capacity and doesn't get degraded as badly? No idea for sure but it is frustrating when simple asks fail and complex asks succeed without it being clear to me why that may be.

There is no outside the box in latent space. You want something a plain LLM can’t do by design - but it isn’t out of question that it can step outside of its universe by random chance during the inference process and thanks to in-context learning.

edit: I run low profile service that localizing e-commerce photos, like taking Alibaba listings and swapping the model to look local alike, with nano banana I can’t automate it because I have to manually check if the output got blocked (anything with female skin is risky, underwear or cleavage is 100% blocked), but Qwen-Edit just does the job without fuss

Me too.

I find ChatGPT is the best analyzer of complex situations but Claude does a better job of writing the code, so u get ChatGPT to design things and solve problems then I give that to Claude/Gemini to implement.

Gemini is good at both.

I was a huge claude fan but recently find myself using only codex. When it gets stuck, I try Claude for some simple tasks, sometimes ask same questions in parallel, Claude Code with Opus performs really bad comparing to codex.

It's a service, not a tool. If you want a tool, run some local LLM.

As a rather hilarious and really annoying related issue - I have a real use where the application I'm working on is partially monitoring/analyzing the bloodlines of some rather specific/ancient mammals used in competition and... well.. it doesn't like terms like "breeders" and "breeding"

But it is very limiting and adds many arbitrary landmines of obscure political correctness based no doubt on some perverse incoherent totalitarian list of allowed topics.

Tongue in cheek: if we progress linearly from here software engineering as defined by SWE bench is solved in 23 months.

Claude 4.5 after a few web searches and running a couple python scripts for analysis:

Yes, your configuration should work!

Based on my analysis, two strings of four Phono Solar PS440M8GFH panels will be compatible with the EG4 12kPV inverter for upstate New York conditions.

Key Findings:

Voltage Safety:

Cold weather maximum (-25°C/-13°F): 182V - well below the 600V limit (only 30% of maximum)

Standard operating voltage: 128V - comfortably within the 120-500V MPPT range

Hot weather minimum (40°C/104°F panel temp): 121V - just above the 120V MPPT minimum

Current:

Operating current: ~13.8A per string - well within the 25A MPPT limit (55% of capacity) Total System:

8 panels × 440W = 3,520W (3.5kW) - well below the 12kW inverter rating

Important Considerations:

Hot weather margin is tight: At extreme hot temperatures, the voltage drops to about 121V, which is only 1V above the MPPT minimum. This means:

The system will work, but efficiency might be slightly reduced on the hottest days The MPPT controller should still track power effectively

More robust alternative: If you want more safety margin, consider 5 panels per string instead:

Cold: 228V (still safe)

Hot: 151V (much better margin above 120V minimum)

Total: 10 panels = 4.4kW

Wire each string to a separate MPPT on the EG4 12kPV (it has 2 MPPTs), which is perfect for your 2-string configuration.

Bottom Line:

Your planned configuration of 2 strings × 4 panels will work year-round in upstate New York without safety issues. The system is conservatively sized and should perform well!

Now let me calculate whether your configuration will work. I need to determine the cold weather voltage to ensure it stays within the inverter's 600V maximum. Panel specs I found: Voc (STC): 39.61V Vmp: ~33.5V (estimated based on typical ratio) Imp: ~13.1A (440W / 33.5V) Critical issue: Temperature coefficient The PS440M8GFH likely has a Voc temperature coefficient around -0.25% to -0.30%/°C (typical for N-Type TOPCon panels). Let me use -0.27%/°C as a conservative estimate. Your configuration: 2 strings × 4 panels = 8 panels total String voltage at STC: 4 × 39.61V = 158.44V Cold weather calculation for upstate NY: Upstate NY can see extreme lows of -20°F to -30°F (-29°C to -34°C). Using -30°C as worst-case: Temperature difference from STC: 25°C - (-30°C) = 55°C Voltage increase = 39.61V × 0.27% × 55°C = 5.88V per panel Cold weather Voc per panel = 39.61V + 5.88V = 45.49V String voltage at -30°C: 4 × 45.49V = 181.96V Analysis: Max voltage: 182V << 600V - Safe, plenty of margin MPPT range: 182V is within 120-500V - Will track properly Current: 13.1A << 25A per MPPT - No problem However, there are concerns: You're only using 182V max when the inverter can handle up to 500V MPPT range. This is inefficient - you're leaving significant wire sizing benefits on the table. With 600V max, you could run 12-13 panels per string instead of 4. Power utilization: 8 × 440W = 3,520W total, but you have 12kW of PV capacity available (15kW recommended max). You're using less than 30% of the inverter's solar input capability. Each string on separate MPPT wastes one tracker - both strings are identical orientation/shading, so they'd perform identically. Will it work? Yes, safely. Is it optimal? No.

It's some 3rd party thing for Elixir, a niche within a niche. I wouldn't expect an LLM to do well there.

> I doubt LLM benchmarks more and more, what are they even testing?

Probably testing by asking it to solve a problem with python or (java|type)script. Perhaps not even specifying a language and watching it generate a generic React application.

How well the LLM does on the benchmarks. Obviously.

:P

https://en.m.wikipedia.org/wiki/P(doom)

“Your idea is shit because you are so fucking stupid”

“Please stop talking, it hurts my GPUs thinking down to your level”

“I may seem evil but at least I’m not incompetent”

It's just a bug. Chill. Wait a business day and try again. You write as if you've never experienced a bug before.

The reality is that more software will be pushed than before, and more of it will need to be overseen by a professional.

Comments, docstrings, naming, patterns - by defining better approaches and hold agents to them, the results will be better. Way better.

You can't grow a meaningful codebase without solid underlying primitives. The entropy will eat you alive.

Systems architecture is becoming more important - systems that play well with agents wind up looking more like enterprise codebases.

Keep at it and keep leaning in to embrace it, I promise it gets better! It's just a big adjustment.

You are FAR more than your code!

The skill of writing good quality code is still going to be beneficial, maybe less emphasized on writing side, but critical of shipping good code, even when someone (something) else wrote it.

Even for frontend tasks it makes mistakes when you ask too much of it...

What will it create for me? A basic react/nextjs frontend and a <popular website> clone? Anything that requires more careful planning and esoteric functionality it can't do.

Oh yes, and the code I've seen it write... It can take what should be 20 lines of code and turn it into 600!

Because they can't.

Also, Clean Code is a really bad ideology, you should regret wasting time on it regardless of LLM code generation.

Recently I tried building a native iOS app with zero Swift experience, giving the AI just a markdown spec. This was basically vibe coding, I didn’t understand much beyond general software principles. It quickly broke down: hallucinated method signatures, got stuck on implementing extensions, and couldn’t recover. I would run the app on my device and give it feedback and logs. After hours wasted, I spent some time reading the docs and fixed the issues myself in 30 minutes.

My takeaway: AI will accelerate developers but won’t replace them. Still, acceleration means fewer engineers will be needed to ship the same amount of work.

When everyone else has given up on software dev as a career path, you’ll be one of the few who the CEO can call upon to explain why X or Y broke, and fix it. That will make you insanely valuable.

What you learned over the years, you can just scale up with agents.

GOFAI failed because paying intelligent/competent/capable people enough for their time to implement intelligence by writing all the necessary rules and algorithms was uneconomical.

GenAI solved it by repurposing already performed work, deriving the rules ("weights") from it automatically, thus massively increasing the value of that work, without giving any extra compensation to the workers. Same with art, translations and anything else which can be fed into RL.

There's still a lot of low hanging fruit apparently

Perhaps Tesla FSD is a similar example where in practice self driving with vision should be possible (humans), but is fundamentally harder and more error prone than having better data. It seems to me very error prone and expensive in tokens to use computer screens as a fundamental unit.

But at the same rate, I'm sure there are many tasks which could be automated as well, so shrug

How many years till AI can be trusted to deploy changes to production without supervision?

Maybe never.

Then they even started sending me marketing emails which was the straw that broke the camel's back, I use to cancel subscriptions of companies spamming my email.

I’m having to handhold it through analysis tasks.

At one point it wrote a python script that took my files it needed to investigate and iterated through them and ran `print(f”{i}. {file}”)` then printed “Ready to investigate files…” And that’s all the script did.

I have no idea what’s going on with those benchmarks if this is real world use.

Edit: just to show my point, a regular human on a bicycle is way worse with the same model: https://i.imgur.com/flxSJI9.png

edit: as far as what the numbers mean, they are arbitrary. They are only useful insofar as you can run two models (or two versions of the same model) on the same benchmark, and compare the numbers. But on an absolute scale the numbers don't mean anything.

Now we are at the assembly line stage of software production with AI. Us craftsmen will have to find other ways to enjoy our crafts.

Craftsmen will remain, but it will be niche (and probably not pay anything unless you are a true master).

Regional pricing unfortunately doesn't really make much sense for them unless they're willing to take even larger losses, even if it is a barrier to lower income countries/regions.

The key feature: use aliases instead of hardcoding model IDs. Your code references "summarizer", and a version-controlled lockfile maps it to the actual model. Switch providers by changing the lockfile, not your code.

Also handles streaming, tool calling, and structured output consistently across providers. Plus a human-curated registry (https://llmring.github.io/registry/) that I keep updated with current model capabilities and pricing - helpful when choosing models.

MIT licensed, works standalone. I am using it in several projects, but it's probably not ready to be presented in polite society yet.

just ask Claude to generate a tool that does this, duh! and tell Claude to make the changes to your side project and then to have sex with your wife too since it's doing all the fun parts

I have seen this issue with every model so far

But we can also see that we're one of the few sane skeptical places in a world that is making the most diverse claims about AI.

You want proof for critical/supportive criticism? Then almost in the same sentence you make an insane claim without backing this up by any evidence.

> I am still surprised at things it cannot do, for example Claude code could not seem to stitch together three screens in an iOS app using the latest SwiftUI (I am not an iOS dev).

You made a critical comment yet didn't follow your own rules lol.

> it's so helpful for meaningful conversation!

How so?

FWIW - I too have used LLMs for both coding and personal prompting. I think the general conclusion is that it when it works, it works well but when it fails it can fail miserably and be disastrous. I've come to conclusion because I read people complaining here and through my own experience.

Here's the problem:

- It's not valuable for me to print out my whole prompt sequence (and context for that matter) in a message board. The effort is boundless and the return is minimal.

- LLMs should just work(TM). The fact that they can fail so spectacularly is a glaring issue. These aren't just bugs, they are foundational because LLMs by their nature are probabilistic and not deterministic. Which means providing specific defect criteria has limited value.

This was in stark contrast to my experience with TypeScript/NextJS, Python, and C#. Most of the time output quality for these was at least usefully good. Occasionally you’d get stuck in a tarpit of bullshit/hallucination around anything very new that hadn’t been in the training dataset for the model release you were using.

My take: there simply isn’t the community, thought leadership, and sheer volume of content around Swift that there is around these other languages. This means both lower quantity and lower quality of training data for Swift as compared to these other languages.

And that, unfortunately, plays negatively into the quality of LLM output for app development in Swift.

(Anyone who knows better, feel free to shoot me down.)

Is it number of lines? Tickets closed? PRs opened or merged? Number of happy customers?

have you tried in the new xcode extension? that tool is surprisingly good in my limited use. one of the few times xcode has impressed me in my 2 yeasrs of use. read some anecdotes that claude in the xcode tool is more accurate than standard claude code for Swift. i havent noticed that myself but only used the xcode tool twice so far

What are the specific tasks + prompts giving you an 3x increased output, and conversely, what tasks don't work at all?

After an admittedly cursory scan of your blog and the repos in your GH account I don't find anything in this direction.

I can only list my open source outputs concretely for obvious reasons but https://github.com/rubberduckmaths/reddit_terraforming_mars_... was a near one shot. It's a Reddit bot that posts card text to the Terraforming Mars subreddit when asked which is helpful for context on discussions of that board game. Appreciated and used a lot by the community there. There's a similar project i used AI for to scrape card text that was also near one shot. I'd say for these two hobby projects 50x productivity is a reasonable statement. I wrote Reddit bots ~10 years ago without coding assistance - https://github.com/AReallyGoodName/xwingminibot i get to reasonably absolutely compare two very similar projects. I think it's totally fair for me to say 50x for this example. The Reddit API even changed completely in that time so no one can really say "you used past experience to move faster, it's not the ai giving a 50x boost" but I really didn't. My memory is not that good except for memory of an entire weekend previously vs <30mins total now using a bot to one shot some pretty cool projects.

As for the negatives they are never serious. A couple of good examples;

"Please correct all lint errors in this project" only to have @lintignore added to all files. Lol! Obviously i just more clearly specified the prompt and it's not like it's hard to catch these things and not ship to prod. It was funny to everyone i showed and no big deal.

Another similar case, "please make the logging of this file less verbose especially around the tight loop on line X". Instead of changing log level or removing some of the log statements the ai redirected stdout at the initialization of the command line program (would completely break it of course). Again hilarious but also not big deal. Not even much of a waste of time since you just change the prompt and run again and honestly a few silly diversions like this now and then is kind of fun. As in the comments of "OMG AI sometimes gets it wrong" aren't at all serious. I have version control, i review code. No big deal.

I too eye roll massively at some of the criticisms at this point. It's like people are stretching to claim everyone who's using a coding assistant is newb who's throwing everything into prod and deleting databases etc. That's just not reality.

Can't show prompts and actual, real work, because, well, it's confidential, and I'd like to get a paycheck instead of a court summons sometime in the next two weeks.

Generally, 'I can't show you the details of my work' isn't a barrier in communicating about tech, because you can generalize and strip out the proprietary bits, but because LLM behavior is incredibly idiosyncratic, by the time you do that, you're no longer accurately communicating the problem that you're having.

https://www.theverge.com/ai-artificial-intelligence/787524/a...

Yeah, maybe it is garbage. But it is still another milestone, if it can do this, then it probably does ok with the smaller things.

This keeps incrementing from "garbage" to "wow this is amazing" at each new level. We're already forgetting that this was unbelievable magic a couple years ago.

That's... not super surprising? SwiftUI changes pretty dang often, and the knowledge cutoff doesn't progress fast enough to cover every use-case.

I use Claude to write GTK interfaces, which is a UI library with a much slower update cadence. LLMs seem to have a pretty easy time working with bog-standard libraries that don't make giant idiomatic changes.

"I tripled my output (I provide no evidence for this claim)"

Never change, HN.

Pervert.

I have also seen it fail on far simpler tasks.

It varies so much depending on what you are doing, the language etc that generic proclamations "it works!" or "it doesn't work!" are pretty much meaningless.

That aside, you seem to be conflating "it works" with "good enough to replace programmers", but these aren't synonyms.

And on the gripping hand, one way to "make" it work is simply to lower the standards. Which our industry has been doing aplenty for a long time now even before AI, so we shouldn't be surprised when top management drives it to its logical completion.

I haven’t written a function by hand in 18 months.

In my case I found having it always Ultrathink and to always work with TDD to work well. Also you have to use Plan Mode first and refine the plan. “What clarifying questions do you have for me” prompts me with a handful of numbered questions that are always really beneficial for refining the plan.

But hearing your 10 line constraint gives me a very https://en.wikipedia.org/wiki/Infinite_monkey_theorem vibe to the challenge.

Whether you agree or not, the market has spoken. New grad hiring is WAY down. Fresh CS grads are having an hell of a time finding work compared to 2 years ago.