Viewing profile — Yopolo

No clue why you have to respond like this. Feel free to be a dick to someone else.

We have the same issue and now spending more time/energy on optimizing the code review agent. This might lead to more automatisation and not less if it works. After all we might ex…

No clue? I don't think they are totally usesless. And its clear that progression is happening on a communith level on all of these and they get integrated later on in commercial of…

Thats just not true and we see this in medicine and research. An expert in physics still needs to write code in python to do their math and analysis. Its an intelligence issue. Tha…

It learned a concept of a heuristic which made it smart enough for the learning reward. Might be an architecture issue or a parameter size issue that it didn't learn to do math lik…

I'm curious if LLM could easily be manipulated to actually process data in context and remove it from its context and replace it with the result or a hint. Might break the caching,…

> Please elaborate. How? With which technique? Reinforcement learning can just solve things even if they are new. It doesn't understand how a tool works? Give it a vm with the tool…

Yes this is unfortunate and not what I meant. I mean the token prices in general as certain services were never really using a subscription. I do run a claude subscripton right now…

We just put different things together and then we evaluate it. In math its simple: does the verification say its okay. If its mechanical: is any property better than what we have a…

> So you mean AI will be useful for any general job without lots of training for those jobs? How about new tasks? I'm pretty sure we will solve this issue. Either already through W…

I'm waiting for the agentic ai platform layer. We see AI factories going in this direction but there is no real 'the open source ai platform' thingy. It needs connectors to integra…

And without an LLM you wouldn't even try? I don't mind semi-deterministic for plenty of things. But these agents like hermes, can codify a skill to be deterministic.

> shifting the work elsewhere for specialized tasks. More replicable, improved, but, it scales infinitely and is autonomous? Can you assert that? I would say yes and it will scale.…

"become more linear starting in Q4" We are not even close to what AI slowdown looks like. The whole business side of things are now building Agentic Layer for Business applications…

Then yeah you might not be a good developer. LLMs are also quite good in writing unit tests and understanding bugs a lot faster than I do, now. Just a few month back i looked at so…

I for sure do plenty of things with AI a lot faster. Instead of searching some linux issue, i will prompt claude to generate a small analyser script for checking wha tlinux i have,…

We switched from looking at an UI (claude webui) and waiting for code generation to using claude exclusivlie on the cli and claude doing a lot more stuff in the background with sma…

In my company GitHub CoPilot was rolled out on a global scale last year. LLMs from Anthropic and co we get through a central tool which buys api tokens from Azure and AWS. Its surp…

LLM don't work on 'compressed data'. LLM compress data into their latent space which allows them to become general. They learn the concept of things and how to do them because this…

It still makes a massive difference for me if they only need a handfull people now. Generating a good looking UI for example, is so much easier now with LLM. For a joke I asked Cha…

No we don't know your 'points' The Hallucinations are becoming less, significantly by now. It also might be already were it is cheaper for one of the big few companies to spend mil…

Java as a programming language doesn't enforce any architecture. There is no difference to go. Its a system of folders. The tests need to be green, the math needs to math, but the …

Besides that i still think its wayy to early to put AI in front of center of everything, the current progress at least makes it clear that is not going to stay as it is. Noneethele…

AI doesn't need to be deterministic.

Start extracting specs from the codebase. Prompt the core architecutre well suited for it. Let it write tests. Let it vibe migrate from left to write. Now you at least have a chanc…