Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Microsoft starts canceling Claude Code licenses

theverge.com

Post reply on HN
Print view View original

231–240 of 489 posts

Re: Microsoft starts canceling Claude Code licenses

#231

Post by jdsnape »

matheusmoreira wrote: post #182
tra3 wrote: post #5

There's definitely a way to use Claude code that is token conscious. I've tried throwing unsupervised agentic software factory workflows against the wall, and they burned through my tokens like nobody's business but didn't produce much. Supervised, human-in-the-loop process on the other hand is much more productive but doesn't consume nearly as much. Maybe that's why everyone's pushing agentic approaches so much.

Yeah. Claude does good work but reviewing it all properly takes quite a bit of time. It got to the point I started having trouble maxing out my weekly allocation. Dealt with that by going all out and making an agentic parallel code review skill. Basically an infinite TODO list generator. Now I'm definitely getting 100% of the usage I paid for. It really burns tokens like nobody's business, and catches a lot of issues…

I’m interested in how this works in practise - I guess you’ve written a skill to do code review, then your Claude.md file tells it to use it after every change as a bg task? So does this work as a background task while Claude is working on the next ‘feature’?

Re: Microsoft starts canceling Claude Code licenses

#232

Post by greenchair »

serf wrote: post #191
salawat wrote: post #29

Earlier quoted context omitted.

There's no fucking training to mitigate a slot machine.

that analogy is so boring now with so many real world examples of actual LLM work. people still can't get over the unreasonable effectiveness of algorithms.

nondeterminism will always be anathema to the engineering mind

Re: Microsoft starts canceling Claude Code licenses

#233

Post by cbdevidal »

mellosouls wrote: post #217
cbdevidal wrote: post #209

Earlier quoted context omitted.

There’s a new plan? Ugh. I signed up about five months ago.

Yes, unfortunately. eg. discussions below - I think I have seen multipliers of 9x cost to existing use cases: Changes to GitHub Copilot individual plans https://news.ycombinator.com/item?id=47838508 GitHub Copilot is moving to usage-based billing https://news.ycombinator.com/item?id=47923357 Multipliers for annual subscribers: https://docs.github.com/en/copilot/reference/copilot-billing...

Thanks for the heads up. I had a brainstorming session with Gemini about this (I can’t believe I just typed that sentence lol) and the plan is to switch to two local LLMs; a lightweight, fast 3B model for autocomplete, and a slower 14B model for chat sessions. Then I can switch to a DeepSeek Premium API key for the really tough stuff. It recommended the Continue plugin for VSCode.

When I am away from home I’ll run autossh on my dinosaur road laptop (which probably has 8MB video RAM lol) to connect to the home PC’s LLMs. Gemini assured me that this should run well over my intermittent cellular connection.

You just saved me some headache and money :-D

Re: Microsoft starts canceling Claude Code licenses

#234

Post by techpression »

meowface wrote: post #223
fendy3002 wrote: post #220

Earlier quoted context omitted.

4.7 is better if your spec is clearer. 4.6 is better if you give it more freedom doing it's tasks. 4.6 felt it'll steer off often if you give detailed specs than 4.7 though, so perhaps that's it

Agreed. 4.7 is a smarter but weirder model. It will get confused in unexpected ways, but when it's not confused it will perform better than 4.6. It's not a bad idea to skip it and wait until the next model release, but I personally will stick with 4.7.

That is a load-bearing decision!

Re: Microsoft starts canceling Claude Code licenses

#235

Post by willtemperley »

comboy wrote: post #194
gofreddygo wrote: post #190

Earlier quoted context omitted.

For months, Employees had the option to choose claude code or copilot. Now they dont. Underlying model choice still has no restrictions. Opus 4.6 is by far the most popular. there's still big $$$ bills going anthropic's way.

Curious if anyone around here stayed on 4.6 (having a choice to use 4.7)

I don't want to change from 4.6 because I'm finding it so good (I could change).

I've spent the last couple of days building Swift bindings to a monster CPP lib and I've actually had fun.

Re: Microsoft starts canceling Claude Code licenses

#236

Post by matheusmoreira »

jdsnape wrote: post #231
matheusmoreira wrote: post #182

Earlier quoted context omitted.

Yeah. Claude does good work but reviewing it all properly takes quite a bit of time. It got to the point I started having trouble maxing out my weekly allocation. Dealt with that by going all out and making an agentic parallel code review skill. Basically an infinite TODO list generator. Now I'm definitely getting 100% of the usage I paid for. It really burns tokens like nobody's business, and catches a lot of issues…

I’m interested in how this works in practise - I guess you’ve written a skill to do code review, then your Claude.md file tells it to use it after every change as a bg task? So does this work as a background task while Claude is working on the next ‘feature’?

I just committed the skill to my dotfiles repository.

https://github.com/matheusmoreira/.files/tree/master/~/.clau...

There are many "critics", one for each quality I want reviewed. Correctness, consistency, maintainability, security, testing... Everything I could think of, and I keep adding more.

https://github.com/matheusmoreira/.files/tree/master/~/.clau...

The scrutinize skill is the entry point. The Opus I'm talking to becomes an agent coordinator. He explores and autodiscovers the project's structure, subdivides it into logical sections.

Then he runs a truly absurd critic x section matrix against the entire project. Literally hundreds of these agents running in parallel, each focusing on one area. Ten minutes of this is enough to exhaust my Max 5x five hour window and put a serious dent in the weekly usage numbers.

It literally takes days to run a full agent sweep. I designed it around the rate limiting. The agents do file system style journaling in order to resume cleanly. They commit all of their findings as they go into an orphan branch in the repository. Further review runs can build on it and avoid searching for known issues.

The way it works in practice is I just run /scrutinize sweep and then go work on something else, or just go do my actual job, live my life, play video games, write an article for my blog or something. Come back five hours later to either resume the process or check the literally hundreds of issues that have been found by all the agents. Then Claude and myself will go in and evaluate and fix all of those issues one by one. Then review again. Then evaluate/fix again. I'm just gonna keep looping this over and over until zero issues are found. For all of my projects.

Going from solo hobbyist programmer to this was pretty insane. I can only imagine what these corporations with infinite money must be doing.

Re: Microsoft starts canceling Claude Code licenses

#237

Post by ninjagoo »

cfunderburg wrote: post #161
iamflimflam1 wrote: post #157

From reading the article. They offered their developers both Claude code and Copilot. What they wanted was for them to use both and feedback which was better. The developers voted with their feet and didn’t use Copilot. What Microsoft were hoping was that the opposite would happen...

I wish I could understand the appeal of using Claude Code inside VScode rather than Copilot. I feel like I'm missing something obvious.

> I wish I could understand the appeal of using Claude Code inside VScode rather than Copilot

MS thinks CoPilot is the Clark Griswold of LLMs when it's really Cousin Eddie...

Re: Microsoft starts canceling Claude Code licenses

#238

Post by ThunderSizzle »

NiloCK wrote: post #202
serf wrote: post #184

Earlier quoted context omitted.

the obvious answer is because it's easier , faster, and more efficient to flip a true to false right in front of you than it is to prompt an llm. if your response is "my prompts don't produce code that needs values flipped, ever." then I would wager you're only touching very simple things with an LLM. for me I don't care about the token cost and prompt writing so much as the fact that it's just faster to change 0 to…

The thing that drove me away from manual edits was that I found myself confusing the LLM all the time. It would read or write, some code, I'd twiddle with things, and then the LLM's future references to the same code would be a mess. On balance, and via dictation, it feels likely to be faster overall to just enact the changes I want 'inline' of the conversation thread. Is this stuff any better now? I think current ha…

If you do manual edits, I find it best to start a new conversation. But if your instructions and documentation is good enough, the new conversations won't have any problems picking up where it needs to be.

Having said that, I fear what June 1st brings for copilot It might suddenly be very useless for me.

Re: Microsoft starts canceling Claude Code licenses

#239

Post by vovavili »

mattmanser wrote: post #174
cfunderburg wrote: post #161

Earlier quoted context omitted.

I wish I could understand the appeal of using Claude Code inside VScode rather than Copilot. I feel like I'm missing something obvious.

I'm a little the opposite, what's the point of using an IDE with AI? I genuinely don't get it? These days I just use Claude Code Desktop or Claude Code in powershell. Standalone, not inside and IDE. Honestly, I'm using Desktop more and more as it gets more features. The IDE is for me. No AI in it at all. If I want to get Claude to do something specific to a file I just @ the file.

Productivity. You generate the skeleton of the code with Codex/Claude Code/et. al. and refactor it manually. It's kind of unlikely that an AI agent will be able to one-shot every bit of code in the exact way you want, even with a fat AGENTS.md file. With a smart AI-native IDE like Zed, it will quickly be able to pick up what manual change you intent to do without you fully typing out anything, especially if they're repetitive. This helps enormously when you're debugging or profiling your code.

Re: Microsoft starts canceling Claude Code licenses

#240

Post by ninjagoo »

relevant_stats wrote: post #102

So, snippet from the article says the following: > I understand that Microsoft is planning to remove most of its Claude Code licenses and push many of its developers to use Copilot CLI instead. While Claude Code has been a popular addition, it has also undermined Microsoft’s new GitHub Copilot CLI coding tool — a command line version of GitHub Copilot that runs outside of development apps like Visual Studio Code. And…

> Is this Hacker News or rather Marketing Wars?

No public forum is naturally immune to the spread of (guerilla) marketing. [1]

[1] Internet Rule #48

Post reply on HN