prettyblocks

No opinion on the salary, but just because it's a once per year event doesn't mean the work isn't year round.

How can this ever be enforced?

My problem is how hot they run. I'm on an m4 pro. Do you have the same issue?

I disagree. iPhones, EVs, and a lot of architecture is really slick looking.

The frontier labs seem to be sandbagging the full capability of the models available in the name of "alignment", which is unfortunate.

This works pretty well for these coding harnesses though (see Pi). I like the model where the harness ships with minimal tools and you can spin up plugins for extra functionality. You can usually have the model/harness you're using just create the plugin that you need for you. The advantage of this is that these harnesses aren't optimized for their frontier models like claude/codex are so you can fine tune your environment and burn less tokens... having said all that, I haven't tried this one yet.

In what dystopian black mirror alternate reality can anyone possibly perceive this as saving the profession of programming? It sounds like hell.

Maybe it improved in the last year but it's substantially worse than before it became X. Back then the algorithm was tuned to align with the users interests and posts would get visibility based on engagement. Now it's still a cesspool and visibility is pay to play.

I always thought that the frontier coding models were specifically trained to perform well in the harness from their providers. I imagine this will always be the case to some extent.

I imagine most people that get into entrepreneurship do so precisely because they don't want to go work for someone else.

The difference is that Anthropic engineers have infinite tokens to throw at these problems for free. The rest of us do not and that's where optimizations in how the coding harness is used likely helps the most.

But many people are doing just that, automating workflows through prompt templates and skills.

> I can’t help but wonder whether constant use of “agent” harnesses will lead to an atrophy of the software engineering (or really any field) muscles.

It will, but I'm not sure the impact of this will be all too great. We suffer from not knowing how to use an abacus because we have a calculator, and people who feel a pull to keep their low-level chops up will do so anyway.

The default system prompt is so lean:

https://github.com/earendil-works/pi/blob/main/packages/codi...

Yes, if you're just going down a list of jira tickets and implementing product features, but for many folks it's also an art medium.

Mostly yes, but I think it's both, because some people become life long fans, like the adult Pokemon card collectors.

In my experience most people with the type of critique I'm seeing from you have only tried it one time or have not taken the time to invest in an environment/process that will work for agentic coding.

My question is not so much about sharing a cherry picked example, but the question was more like "have you tried in earnest to make it work". That's the part that wasn't clear from your original post. But you say you have, and you weren't impressed. Fair enough. I'm not trying to convince you otherwise, but I encourage people to give the tools a fair chance before throwing up their hands and deciding it's meh.

Having said all that, you're right there isn't a shared experience.

I'm curious. What have you actually tried? Are you just prompting the LLM with one off tasks? For good results, you need to take the time to read the documentation for the harness you are using and configure your environment. This tuning can take dozens hours to nail down. Then there's the actual approach for working on your projects. Many people that have good results with agentic coding actually spend the bulk of their time in plan mode where they go back and forth with the LLM designing a granular playbook for the task at hand before they ever have it write any code.

#2 is not really an option though. It's more like #1 or #3.

If you use lmstudio it will tell you which models will fit in what you've got available.

It's great, but I wish I could use these things without it feeling like my laptop is going to melt through the desk.

You can also use JS to inject a CSP and it will enforce the strict most policy.

There are paid solutions for this, I've seen Exa recommended.

I've been relatively impressed with local llms, but by far the hardest thing for me is how hot they make my laptop run.

I believe it's 9k/year in parking revenue.

> However, in hindsight, Leary proved to be a false prophet who helped destroy the 1960s movements by pushing young people to take a drug that fried their brains and diverted their energy from political activism.

This is a pretty bogus claim. False prophet maybe, but the idea that political activism fizzled out because everyone was eating acid seems pretty unsubstantiated.

Back in the day when I was in HS, kids would go to Borders and swap the stickers from cheap books onto expensive computer books.

For me the vision/OCR is much better than other models in weights class.

> Yes ai can’t see, it only understands numbers.

I've also used AI to build frontends that I'm more than satisfied with, and I think it can "see" perfectly fine. The frontier models are multi-modal and pretty good at vision. You can hook up your coding harness to your browser which will take screenshots of your rendered frontend and modify the code accordingly.

I think it's safe to assume that "AI help was used" in everything these days and I don't understand why that should be a problem.