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

481–489 of 489 posts

Re: Microsoft starts canceling Claude Code licenses

#481

Post by onlyrealcuzzo »

shomp wrote: post #479
onlyrealcuzzo wrote: post #469

Earlier quoted context omitted.

> This only works if there's no consequences if your code breaks. In the eyes of other humans you're responsible for what you commit. No amount of "scaling" will change that. You're only responsible for what you merge to master, not everything you commit to a feature branch no one is looking at... If you have the testing and the infrastructure in place such that you can't ship broken code, then you just need to make…

So you're making a programming language... and you don't want to read code. Have I got the gist of it?

At a proof of concept stage for a research language? Why on earth would I?!

For one, a project of this scale is literally completely unfeasible if you're reviewing every line hand by hand - or at least for me when this is a very minor side project...

It's a 1M+ line scope...

The odds it gets completed is not 100%.

The odds it turns out as well as I would like is not 100%.

The odds anyone ever uses it besides me even if it does is not high.

And the entire purpose of the project is to test how well LLMs can actually scale, which, as I mentioned, REQUIRES not reviewing every line with a jade handled magnifying glass...

Re: Microsoft starts canceling Claude Code licenses

#482

Post by Obscurity4340 »

williamDafoe wrote: post #417
rcleveng wrote: post #413

Earlier quoted context omitted.

Slowly and then suddenly :) """ Steve Ballmer In IBM there's a religion in software that says you have to count K-LOCs, and a K-LOC is a thousand line of code. How big a project is it? Oh, it's sort of a 10K-LOC project. This is a 20K-LOCer. And this is 5OK-LOCs. And IBM wanted to sort of make it the religion about how we got paid. How much money we made off OS 2, how much they did. How many K-LOCs did you do? And we…

So many times in my career I have seen a problem that could be handled with two lines of code and a table lookup being handled with 40 lines of code and a switch statement. So the guy writing the 40 lines of codes switch statement would get paid 20 times more money!

MonieS!

Re: Microsoft starts canceling Claude Code licenses

#483

Post by jwoq9118 »

rplnt wrote: post #170
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.

Slightly related (me not understanding) is why the Copilot in VS code is essentially just CLI interface. Why can't it use the IDE tools (search, LSP, ...). All it ever does is trying to execute grep.

I'm not sure how you can believe that GitHub Copilot in VS Code is just a CLI interface when the former existed long before the CLI. It's not. For a certain amount of time, the two teams weren't even working together. The CLI was adding things customers were wondering when would it reach VS Code. So, it's not just a CLI harness. They added the ability to call the CLI from VS Code but GitHub Copilot in VS Code existed before the CLI and is remains a separate thing that's just interfacing with the CLI now.

All I can say is I know because I know. There's been some "synergizing" among the corporation about the CLI team running off to do their own thing and adding features to the CLI that amount to trying to force a Terminal to act like a GUI.

Re: Microsoft starts canceling Claude Code licenses

#484

Post by liamwire »

arkadiytehgraet wrote: post #468
solenoid0937 wrote: post #457

Earlier quoted context omitted.

> What does frequency bias have to do with the objective fact that hundreds of people reported This isn't hard to understand "Model is nerfed" claim hits social media Someone else sees it, frequency bias makes them think their model is also nerfed, and they amplify the claim Now it spreads, like a virus, even if the model never changed Social dynamics like this are well understood psychologically > If the LLM used to…

Did your LLM context get blown up or why does your comment read like linkedin-style post with one-liner sentences structure? Did you really just claim that people are so gullible that it was social media or whatever that made them believe their LLM could no longer achieve the tasks it yesterday could, and not the actual FACT of LLM not being able to do it that they, you know, verified before complaining online? I gue…

My god, man. Go read the HN guidelines, this method of communication isn't only insufferable to read, but is actively making this place worse to be a participant of.

Re: Microsoft starts canceling Claude Code licenses

#485

Post by toponijo »

theptip wrote: post #390
bob1029 wrote: post #363

Earlier quoted context omitted.

I think quantifying tokens used is analogous to quantifying the amount of sawdust generated on a construction site. Churning out useful code quickly is not solved by using more tokens per unit time. Most non-technical leaders can grasp this one and are likely more interested in the strategic game theoretical dynamics that are being forced by way of implied token consumption expectations (competition between developer…

To understand the token count thing - spending tokens is necessary and not sufficient to demonstrate that you are adopting AI. Where we were 6mo ago is that a lot of big orgs realized they were behind, and needed some way of measuring if the tools were usable at all. No sawdust at all on your job site, and you can tell nobody is cutting wood. Now that tooling is more mature, you can measure things like % of diffs AI-…

No sawdust means no tokens. Maybe there were already enough planks around. Maybe a task was completed without AI. What matters is what was done and not whether there's sawdust / AI was used.

Re: Microsoft starts canceling Claude Code licenses

#486

Post by lukebitts »

arkadiytehgraet wrote: post #468
solenoid0937 wrote: post #457

Earlier quoted context omitted.

> What does frequency bias have to do with the objective fact that hundreds of people reported This isn't hard to understand "Model is nerfed" claim hits social media Someone else sees it, frequency bias makes them think their model is also nerfed, and they amplify the claim Now it spreads, like a virus, even if the model never changed Social dynamics like this are well understood psychologically > If the LLM used to…

Did your LLM context get blown up or why does your comment read like linkedin-style post with one-liner sentences structure? Did you really just claim that people are so gullible that it was social media or whatever that made them believe their LLM could no longer achieve the tasks it yesterday could, and not the actual FACT of LLM not being able to do it that they, you know, verified before complaining online? I gue…

Having read this whole conversation (much like one feels the need to stare at a car accident), you sound truly insane. I hope that’s you were aiming for, otherwise you really need help

Re: Microsoft starts canceling Claude Code licenses

#487

Post by shomp »

onlyrealcuzzo wrote: post #481
shomp wrote: post #479

Earlier quoted context omitted.

So you're making a programming language... and you don't want to read code. Have I got the gist of it?

At a proof of concept stage for a research language? Why on earth would I?! For one, a project of this scale is literally completely unfeasible if you're reviewing every line hand by hand - or at least for me when this is a very minor side project... It's a 1M+ line scope... The odds it gets completed is not 100%. The odds it turns out as well as I would like is not 100%. The odds anyone ever uses it besides me even…

Is there a place you are tracking or publishing your findings throughout this "test" ?

Re: Microsoft starts canceling Claude Code licenses

#489

Post by RA_Fisher »

mirekrusin wrote: post #430
RA_Fisher wrote: post #326

Earlier quoted context omitted.

Ah okay, can it work on a whole repo in an agentic way?

Yes, of course, it can also span subagents, work for an hour without interactivity if that's what you want etc. just like any other harness. Actually due to stupid billing system of github which charges per "premium request" instead of tokens, you could and still can abuse it so it costs nothing. They're changing it from next month to usage based billing though.

Ah thank you for updating me there.
Post reply on HN