Slowly the AI craziness at Microsoft is taking the similar shape, of going all in at the begining and then losing to the competition, that they also had with Web (IE), mobile (Windows CE/Pocket PC/WP 7/WP 8/UWP), the BUILD sessions that used to be all about UWP with the same vigour as they are all AI nowadays, and then puff, competition took over even if they started later, because Microsoft messed up delivery among everyone trying to meet their KPIs and OKRs.

I also love the C++ security improvements on this release.

Facebook got excoriated for doing that with Onavo but I guess it's Good Actually when it's done in the name of protecting my computer from myself lol

I asked 2 things.

1. Create a boilerplate Zephyr project skeleton, for Pi Pico with st7789 spi display drivers configured. It generated garbage devicetree which didn't even compile. When I pointed it out, it apologized and generated another one that didn't compile. It configured also non-existent drivers, and for some reason it enabled monkey test support (but not test support).

2. I asked it to create 7x10 monochromatic pixelmaps, as C integer arrays, for numeric characters, 0-9. I also gave an example. It generated them, but number eight looked like zero. (There was no cross in ether 0 nor 8, so it wasn't that. Both were just a ring)

What am I doing wrong? Or is this really the state of the art?

It's interesting that the highest level of reasoning that GPT-5 in XCode supports is actually the "low" reasoning level. Wonder why.

Headline quite misleading. So not exactly that it will ship in Xcode but will allow connect to paid account.

I bought a Pro subscription, the send button on their dumb chatbot box is disabled for me (on Safari), and I still get "capacity constraints' limits. Filed a chargeback with my bank just because of the audacity of their post-purchase experience. ChatGPT-5 works good enough for coding too.

From my experience with Claude Opus it seems like it tries to be "too smart" and doesn't seem to keep up with the latest APIs. It suggested some code for a iOS/macOS project that was only valid on tvOS, and other gaffs.

I also wonder if it will have separate rate limits from ChatGPT (app/web) and Codex CLI (which currently has its own rate limits).

This isn't going to change my workflow at this point.

My pet peeve is it will try to autocomplete any string you start typing with just random crap it thinks you might want in a string.

Under the known issues

Your first prompt is testing Claude as an encyclopedia: has it somehow baked into its model weights the exactly correct skeleton for a "Zephyr project skeleton, for Pi Pico with st7789 spi display drivers configured"?

Frequent LLM users will not be surprised to see it fail that.

The way to solve this particular problem is to make a correct example available to it. Don't expect it to just know extremely specific facts like that - instead, treat it as a tool that can act on facts presented to it.

For your second example: treat interactions with LLMs as an ongoing conversation, don't expect them to give you exactly what you want first time. Here the thing to do next is a follow-up prompt where you say "number eight looked like zero, fix that".

It’ll successfully produce _something_ like that, because there’s millions of examples of those technologies online. If you do anything remotely niche, you need to hold its hand far more.

The more complicated your requirements are, the closer you are to having “spicy autocomplete”. If you’re just making a crud react app, you can talk in high level natural language.

Trying two things and giving up. It's like opening a REPL for a new language, typing some common commands you're familiar with, getting some syntax errors, then giving up.

You need how to learn to use your tools to get the best out of them!

Start by thinking about what you'd need to tell a new Junior human dev you'd never met before about the task if you could only send a single email to spec it out. There are shortcuts, but that's a good starting place.

In this case, I'd specifically suggest:

1. Write a CLAUDE.md listing the toolchains you want to work with, giving context for your projects, and listing the specific build, test etc. commands you work with on your system (including any helpful scripts/aliases you use). Start simple; you can have claude add to it as you find new things that you need to tell it or that it spends time working out (so that you don't need to do that every time).

2. In your initial command, include a pointer to an example project using similar tech in a directory that claude can read

3. Ask it to come up with a plan and ask for your approval before starting

If you just selected a random developer do you think they're going to have any idea why your talking about?

The issue is LLMs will never say, sorry, IDK how to do this. Like a stressed out intern they just make up stuff and hope it passes review.

When people say things like "I told Claude what I wanted and it did it all on the first try!", that's what they mean. Basic web stuff that that is already present in the model's training data in massive volumes, so it has no issue recreating it.

No matter how much AI fanatics try to convince you otherwise, LLMs are not actually capable of software engineering and never will be. They are largely incapable of performing novel tasks that are not already well represented in their weights, like the ones you tried.

Providing a woefully inadequate descriptions to others (Claude & us) and still expecting useful responses?

You're treating the tool like it was an oracle. The correct way is to treat it as a somewhat autistic junior dev: give it examples and process to follow, tell it to search the web, read the docs, how to execute tests. Especially important is either directly linking or just copy pasting any and all relevant documentation.

The tool has a lossily compressed knowledge database of the public internet and lots of books. You want to fix the relevant lossy parts in the context. The less popular something is, the more context will be needed to fill the gaps.

Ask Opus or Gemini 2.5 Pro to write a plan. Then ask the other to critique it and fix mistakes. Then ask Sonnet to implement

If it doesn't have the underlying base data, it tends to hallucinates. (It's getting a bit difficult to tell when it has underlying data, because some models autonomously search the web). The models are good at transforming data however, so give it access to whatever data it needs.

Also let it work in a feedback loop: tell it to compile and fix the compile errors. You have to monitor it because it will sometimes just silence warnings and use invalid casts.

> What am I doing wrong? Or is this really the state of the art?

It may sound silly, but it's simply not good at 2D

My coding ranges from "exotic" to "boiler plate" on any given day.

> Create a boilerplate Zephyr project skeleton, for Pi Pico

Yea... Asking Claude to help you with a low documentation build root system is going to go about the same way, I know first hand about how this works.

> I asked it to create 7x10 monochromatic pixelmaps

Wrong tool for the job here. I dont think IDE and Pixelmaps have as large of an intersection as you think they do. Claude thinks in tokens not pixels.

Pick a common language (js, python, rust, golang) pick something easy (web page, command line script, data ingestion) and start there. See what it can do and does well, then start pushing into harder things.

That will get you a lot better initial solution. I typically use Sonnet for the sub-agents and Opus for the main agent, but sonnet all around should be fine too for the most part.

The more esoteric your stack, and the more complex the request, the more information it needs to have. The information can be given either through doing research separately (personally, I haven't had good results when asking Claude itself to do research, but I did have success using the web chat UI to create an implementation plan), or being more specific with your prompt.

As an aside, I have more than 10 years of experience, mostly with backend Python, and I'd have no idea what your prompts mean. I could probably figure it out after some google searches, tho. That's also true of Claude.

Here's an example of a prompt that I used recently when working on a new codebase. The code is not great, the math involved is non trivial (it's research-level code that's been productionized in hurry). This literally saved 4 hours of extremely boring work, digging through the code to find various hardcoded filenames, downloading them, scp'ing them, and using them to do what I want. It one-shotted it.

> The X pipeline is defined in @airflow/dags/x.py, and Y in `airflow/dags/y.py` and the relevant task is `compute_X`, and `compute_Y`, respectively. Your task is to:

> 1. Analyze the X and Y DAGs and and how `compute_X` functions are called in that particular context, including it's arguments. If we're missing any files (we're probably missing at least one), generate a .sh file with aws cli or curl commands necessary for downloading any missing data (I don't have access to S3 from this machine, but I do have in a remote host). Use, say, `~/home` as the remote target folder.

> 2. If we needed to download anything from S3, i.e. from the remote host, output rsync/scp commands I can use to copy them to my local folder, keeping the correct/expected directory structure. Note that direct inputs reside under `data/input`, while auxiliary data resides in other folders under `data`. Do not run them, simply output them. You can use for example `scp user@server.org ...`

> 3. Write another snapshot test for X under `tests/snapshot`, and one for Y. Use a pattern as similar as possible to the other tests there. Do not attempt to run the tests yet, since I'll need to download the data first.

> If you need any information from Airflow, such as logs or output values, just ask and I can provide them. Think hard.

There are parts in the codebase I'd love some help such as overly complex C++ templates and it almost never works out. Sometimes I get useful pointers (no pun intended) what the problem actually is but even that seems a bit random. I wonder if it's actually faster or slower than traditional reading & thinking myself.

Generating a state-of-the-art response to your request involves a back-and-forth with the agent about your requirements, having a agent generate and carry out a deep research plan to collect documentation, then having the agent generate and carry out a development plan to carry it out.

So while Claude is not the best model in terms of raw IQ, the reason why it's considered the best coding model is because of its ability to execute all these steps in one go which, in aggregate, generates a much better result (and is less likely to lose its mind).

For your first task - give it smaller steps along the way that you can validate. Provide context where possible (like docs for st7789, examples of other zephyr projects). Use Opus instead of Sonnet for tasks that are on the edge of it's capabilities like this. It will still make mistakes, be prepared for iterating on the design and providing feedback.

For your font example, you always need to validate the output of the LLM, but did it still save you time? If so then I consider that a win. If not, give it the task that it's good at (ie generating the surrounding code and definitions) and then fill in the font data yourself.

Dump your thoughts in a somewhat arranged manner, tell it about your plan, the current status, the end goal, &c. After that tell it to write 0 code for now but to ask questions and find gaps in your plan. 30% of it will be bullshit but the rest is somewhat useable. Then you can ask for some code but if you care about quality or consistency with you existing code base you probably will have to rewrite half of it, and that's if the code works in the first place

Garbage in garbage out is true for training but it's also true for interactions

One frustration was the code changed so much in ChatGPT so had to be lots of prompts. But I had no idea what the code was anyways. Understood vibe coding. Just used ChatGPT on a whim. Liked the end result.

After a few iteration i then ask it to implement the design doc to mostly-better results.

A key skill in using an LLM agentic tool is being discerning in which tasks to delegate to it and which to take on yourself. Try develop that skill and maybe you will have better luck.

Wont work by default if I'm reading this correctly

Also, there are plenty of editors and IDEs that don’t.

Let’s stop pretending like you’re being forced into this. You aren’t.

But I guess the user could still get a 3rd party plugin.

I do not think this will be an issue for big companies.

There's simply no way to properly secure network connected developer systems.

you can use Claude via bedrock and benefit from AWS trust

Gemini? Google owns your e-mail. Maybe you're even one of those weirdos who doesn't use Google for e-mail - I bet your recipient does.

so... they have your code, your secrets, etc.

Otherwise there's VSCodium which is what I'm using until I can make the jump to Code Edit.

If you don’t want to use LLM coding assistants – or if you can’t, or it’s not a technology suitable for your work – nobody cares. It’s totally fine. You don’t need to get performatively enraged about it.