vibeprofessor

true, if everything is 'fascism' then nothing is

yes, 70,000 Gazans, 50k of whom were males of fighting age, no other army managed to achieve such low civilian-to militants casualties ratio, under such extreme war conditions

haaretz is a left wing rag, they are just as trustworthy as hamas health ministry

they are awesome tbh, and i have 3 accounts here dating back from 2008 with something like 10k karma

add another agent review, I ask Claude to send plan for review to Codex and fix critical and high issues, with complexity gating (no overcomplicated logic), run in a loop, then send to Gemini reviewer, then maybe final pass with Claude, once all C+H pass the sequence is done

"Global South"

go woke go broke

yes, i switched to Codex after he mentioned it on "Pragmatic engineer" podcast and I ran out of Claude credits on 20x plan. So far Codex is matching or slightly beating Claude Code for me. Loving the Desktop app despite the slowness

Well OpenClaw has ~3k open PRs (many touching security) on GitHub right now. Peter's move shows killer product UI/UX, ease of use and user growth trump everything. Now OpenAI with throw their full engineering firepower to squash those flaws in no time.

Making users happy > perfect security day one

here is just one example, wikipedia turned into antisemitic propaganda outlet https://x.com/just_whatever/status/2017948781895880726?s=20

It's still work, but a different kind of work. You have this supercomputer that can answer almost any question and build code far faster than you ever could but you need to know the right questions to ask. It's like Deep Thought in The Hitchhiker's Guide: ask the wrong question and you get "42".

it's just across the threads Clawd get a lot of negative sentiment here for whatever reason, while it's such a brilliant hack

>often takes more time than just writing the Python myself in my experience

I guessed you haven't tried Codex or Claude code in loop mode when it's debugging problems on its own until it's fixed. The Clawd guy actually talks about this in that interview I linked, many people still don't get it.

I find hard problems are best solved by breaking them down into smaller, easier sub-problems. In other words, it comes down to thinking hard about which questions to ask.

AI moves engineering into higher-level thinking much like compilers did to Assembly programming back in the day

The AGI vibes with Claude Code are real, but the micromanagement tax is heavy. I spend most of my time babysitting agents.

I expect interviews will evolve into "build project X with an LLM while we watch" and audit of agent specs