471–480 of 512 posts
Earlier quoted context omitted.
Why on earth would you spend any time at all convincing an agent of anything? You say "just do it" and off it goes.
Uh Claude tries real hard to dodge work. Talks about how it’s really hard 10 PRs. Finally convince it to do as 1. It stops 10% through and says ok done with PR 1, we can work on the last 9 tomorrow. Ugh.
Earlier quoted context omitted.
How is neurosymbolic not aligned with the bitter lesson? The bitter lesson is completely agnostic to architecture.
I should have stressed the symbolic part. Everyone has pivoted to symbolic systems like claude code and codex. They would no invest so heavily in such systems if they thought llms would deliver agi soon.
Earlier quoted context omitted.
I hardly notice DeepSeek being inferior to Claude Opus unless I have it working on tricky and under-defined problems. That is, I trust Opus to reason much better when it has the choice. Otherwise, IME DeepSeek is far cheaper and more effective for anything where the solution is even somewhat obvious.
Out of curiosity, what is your stack? And is this in a legacy project or new one? I have tried using deep seek flash and pro but they make amateur mistakes. Sonnet level at best. However v4 flash is absolutely amazing as a generalist model and it’s what we’re using on a product built on top of LLMs. I wish I could code with it but it’s not going to happen anytime soon
Earlier quoted context omitted.
I'm using Deepseek-v4-pro as my main model and this is sometimes pretty annoying, I have to do some easy boring task, think "I'll just leave the agent to do it and go take a nap", but it's already done writing the code before I even walk away from the computer
Agent mania setting in It's also pretty funny sometimes how it gives weird future roadmap estimates ("part 2 - 3 weeks, part 3 - 2 months", etc.) and when you tell it to actually do those changes it's pretty much done in half an hour
Earlier quoted context omitted.
> the estimates It doesn't estimate. It generates tokens that read like estimates associated with the context in its training material. What would you expect the generator to output instead?
This is so 2023. The thought process. At that time the predominant view was that LLMs were nothing but stochastic parrots, that they would plateau, and that hallucinations couldn't be fixed. At this point I doubt there are any AI sceptics left. That ship has long sailed. The only thing that matters is whether the estimates are accurate, and AI can improve on that too. Even humans only estimate based on neurons firing…
Earlier quoted context omitted.
Why on earth would you spend any time at all convincing an agent of anything? You say "just do it" and off it goes.
Uh Claude tries real hard to dodge work. Talks about how it’s really hard 10 PRs. Finally convince it to do as 1. It stops 10% through and says ok done with PR 1, we can work on the last 9 tomorrow. Ugh.
Earlier quoted context omitted.
Out of curiosity, what is your stack? And is this in a legacy project or new one? I have tried using deep seek flash and pro but they make amateur mistakes. Sonnet level at best. However v4 flash is absolutely amazing as a generalist model and it’s what we’re using on a product built on top of LLMs. I wish I could code with it but it’s not going to happen anytime soon
I've used it across many new projects as well as many legacy ones. It does make amateur mistakes so you can't leave it unsupervised for hours like I do with Claude, but it's so much cheaper that weeks of heavy usage haven't even cost me $10 yet. Only other downside IMO is that Pro is pretty slow, even compared to frontier models; only around 120t/s IIRC.
Usually I'm working on a large task, typically with Opus, while also having a bunch of smaller tasks in their own independent worktrees. Those still need supervision, but less. My goal was to get deepseek to drive the cost of those down, but it was too slow and unreliable...
Earlier quoted context omitted.
Flash is amazing if you know the domain really well. E.g. occasionally it makes the dumbest mistakes you've ever seen and can't correct them. However it's fairly rare, and if you know the domain really well, occasionally popping in the code and pushing it towards the correct solution takes like 20seconds or whatever. So the speed you can move with flash + high domain knowledge beats opus by a mile in my experience. I…
Yes, you don't need much domain knowledge to use Opus, but it's just way too expensive.
Or when I'm working two contract gigs. I can spec things out for one and turn it loose and trust it. Then work more closely with deepseek on the other project.
Earlier quoted context omitted.
I had a friend who was CEO of a startup tell me that he typically only “worked” an hour a day, not because he was lazy but just because there was so much nonsense in his schedule. He told me he was trying to get it to two hours per day.
How successful did he turn out to be? As a CEO your days should be jam packed with brutal "chewing glass and gazing into the abyss". Is he running a lifestyle type company?
Earlier quoted context omitted.
> You never know whether Anthropic will route your request to a cheaper model for the price of Opus For non subsidized plans? Pretty sure they'd need to put this in ToS, or law suites would have followed by now.
How can you prove it? Sometimes Opus just gives me a rubbish session.