enraged_camel

I really like the the new ability for agents to start and manage other top-level agents. Makes it super easy to have one agent as the orchestrator for a feature and have it launch new sessions, answer questions from those agents, review their work and build merge trains. This was possible before, but required a fair amount of manual work. Now the experience feels first-class and it's really nice.

Claude Code is not in-flight software though.

Software is very different than other engineering disciplines. It is meant to be malleable. I think you need a better analogy.

The UI has improved substantially over the past six months. New capabilities are prominently featured and less-used ones are de-emphasized or removed. Every product goes through this type of evolution. The difference with Claude Code is that at the speed they iterate, it happens a lot faster and is therefore more noticeable.

>> My best guess is that the uptick in code changes corresponds to the availability of Mythos/Fable-class models inside of Anthropic.

Yeah. OpenAI basically said the same thing with regards to having Astra available to their team internally over the summer.

How does this one instance refute the argument you quoted?

>> I've been mostly using GLM-5.3 on low reasoning, with great results.

Bro come on.

They pushed back the IPO because their finances are a mess and they don't have any models that can give them a decisive edge. Astra was touted as AGI and got crushed by Opus 5.5 two weeks later. That's not the type of thing that fills investors with confidence.

Fable 5.5 is around the corner, and 'Bel' will be out by end of year as well. We don't know how good they are, but if the improvements from Opus 5 to 5.5 are any indication, I think Meta will be left in the dust again pretty soon.

>> Here’s a third one. In some of the code reviews I’ve encountered that AI gives a lot of feedback, it’s just providing noise.

This is completely normal if you haven't written your own custom skill with instructions on what types of issues the AI should emphasize, which ones would be considered nits and which ones aren't a problem at all.

In our repos we use a classification system: blocker, should-fix and nit. Each one has specific definitions, criteria and examples encoded in the skill file. When the time comes to review a PR, agents invoke the skill, and frankly do a stellar job. A human then reads each finding, asks the AI follow-up questions and makes the final decision in terms of whether the finding goes in the PR review.

The reason I know this works is that we have one guy on the team who does not use this skill, and blindly throws his agents at PRs. And the results are exactly as you describe.

>> He catches stuff in code review that I didn’t catch, and claude/copilot didn’t catch.

This, I find completely unbelievable. Because we had (emphasis on had) seasoned engineers on the team who similarly eschewed AI tools and insisted on doing everything by hand in the manner you describe, well after the rest of the team adopted AI. Yet when it came to code reviews, even in parts of the codebase they were familiar with, the bugs they found often came down to nits, bike-shedding and opinion-based feedback (that they usually tried to frame as objective fact). They would also disagree with almost every AI finding, arguing that it was an unrealistic scenario or an edge case not worth worrying about.

Fundamentally, I don't think humans are going to be capable of providing high quality feedback on PRs authored by AI agents unless those PRs are fairly small in lines of code and volume. It's just way too much information and context for one person to keep in their head. I read a statistic that said the average lines of code a senior engineer can read and provide good feedback on is about 400 per hour, and that number goes down the more time they spend doing code reviews. So, to anyone who insists on trying to keep up with AI, I say: good luck.

In law, intent matters. You should look up the difference between murder and manslaughter for example. Each has multiple degrees as well.

Got it. Thanks for your input I guess.

>> that just sounds like openai/anthropic cope/propaganda, based on absolutely nothing objective lol

Nah. There are benchmarks. They are free to look at. And they paint a very clear picture.

Not really. We use Haiku 4.5 to turn users' natural language queries and requests into fairly complex structured specs for interior design and construction. It has near perfect accuracy.

>> Not really, you have to fiddle with generating api keys and setting environment variables.

That's 5-15 minutes of work at most. Not exactly the type of lock-in the parent is implying.

What does "tangled in their api" mean? Switching is pretty easy.

>> 100k tokens is an absurdly low cutoff and it is only applicable to Haiku and not Sonnet or Opus. It's a low enough cutoff that it will be quickly exceeded if you are doing anything with Agents

Your vibes don't appear to be supported by facts. From the announcement:

>> Claude Haiku 5.5 is priced 90% lower than Claude Haiku 4.5 for requests up to 100,000 tokens, and 50% lower for requests over 100,000 tokens. On Haiku 4.5, 90% of requests fell into the former category.

>> Anything I want to (have to*) be able to deploy on a moments notice, for hotfixes and what not, was moved away from Github like a year ago, because of the horrible uptime. Did others not get the memo yet?

This misses the point in a bad way. You shouldn't have a single deploy funnel to begin with. You should be able to do deploys from multiple places.

>> Is there anyone who has not been badly wrong?

Being wrong, even badly wrong, is fine, so long as one adjusts their beliefs accordingly. LeCun has not.

>> You don't need documentation or the 3rd party memory systems. The code IS the documentation.

We have heard this nonsense from the "we don't need to write comments, code should be self-documenting" types for decades. It was wrong in that context, and it is wrong in this one.

Code tells you how a system works. It does not tell you why it works that way. That is what memory is for. It exists so that your AI does not keep undoing past decisions when it writes or refactors code.

Laws will come once an AI-equivalent of 9/11 happens. Like when rogue AI agents take down a power grid or shut down a major hospital network.

>> That doesn't matter because companies who use AI art in their projects either proudly proclaim they're using it

A lot of them have stopped doing that precisely because of the backlash, and others will too soon.

Consumers can almost never tell AI art apart from human art.

I've been able to use Opus 5.5 and Fable 5.1 for defensive security audits without any issues. They cannot do offensive tasks like pen-testing but in a lot of cases that's not a big shortcoming.

>> But GP comment is not about how you feel about it. It is about where you direct that anger.

Don't worry, my anger is limitless and I can direct it at both corporations and corporations at the same time.

Based on some... rumors I've heard, this is their "Pro" offering. There is supposed to be an Ultra coming as well.

Sorry, that distinction makes zero sense. Either way you're paying a monthly opex cost, compared to it being your own hardware, in which case it would be a fixed capital expense. Which is what "your own infra" means. I worked in managed IT services for 15 years. Trust me, the terminology is important and words don't suddenly start to mean what you want them to mean.

>> "Running your own infra" also includes managed infra like Bedrock, Foundry, etc.

Managed infra is, by its very definition, not your own infra. It's infrastructure someone else sets up and manages for you.

Context is useful. The parent said: "it's a cheaper product that's almost as good or better in some cases"

The only open models that are "almost as good or better in some cases" require massive amounts of RAM. I posit that most people cannot afford a decked out Mac Studio, and therefore run the smaller "flash" variants on more normal devices. The issue is that those are nowhere near frontier-level in terms of capability.