philipbjorge

That's how it started for us. Make sure you achieve and maintain great profitability, PE operates very differently from VC.

> When you actually put them to the test you see 500k tokens of reasoning with "Actually..." and "Wait..." in every third paragraph of their reasoning trace.

I've wondered if this is part of why we don't see the reasoning traces for Anthropic's models before -- Open models might just be accurately surfacing how the sausage is made.

I'm writing much more secure software and infrastructure (e.g. IAM now gets configured well).

Wow, I would love to read an interview series based on this!!

It’s been 25 years since I was in school and this was my experience. Unsure if it’s changed…

I’ll second this, I had to send this message…

> based on our discussions so far, I think we’d only need... Which they appear to have but I can't dig in on mobile.

I'll go further and note that some of the optimizations I've seen in rtk for things like `git status` have actually bubbled up into the model layer -- Codex is regularly making tool calls like `git status --short` instead of `git status`.

I can't find the relevant issues in their repo, but I've been somewhat skeptical of their tool over-reporting token savings and there are many issues to that effect in the repo.

I'm not likely to install it again in my latest configuration, instead applying some specific tricks to things like `make test` to spit out zero output exit on unsuccessful error codes, that sort of thing. Anecdotally, I see GPT-5.5 often automatically applying context limiting flags to the bash it writes :shrug:

I've done some pretty incredible things with LLMs. If this were sqlite with its exhaustive test suite... OK, I can see it.

It's hard for me to see this not becoming a pile of slop, but hey, maybe I'm wrong

Been loving pi and codex lately. Good to build resiliency and self sufficiency into these systems.

Can you fill me in on how this impacts conductor? How are they using `claude -p`?

Tracking with `ccusage`, I pretty easily hit $2000/mo in API equivalent credits and while I'd consider myself a power user, I'm a responsible one that's generally always in the loop. If I were using `claude -p`, this would effectively be a kneecapping.

This seems like less of a today thing and more of an ancient human tendency.

A lot of Buddhist practice is basically trying to train against immediately collapsing reality into self/other, right/wrong, craving/aversion.

Practicing this with Elon Musk is effectively ultra hard mode.

--

Though I do think there’s a subtle irony here too — the original commenter may simply be describing their own emotional reaction/disillusionment, while your response risks collapsing them into "part of the problem."

Feels like everybody in the thread is pointing at the same tendency from different angles.

Ahh good point -- I've handled this by switching my harness to `pi` but recognize that may not be for everyone and doesn't directly address OP's question.