+1
Also, prose unlike code is not verifiable, almost by definition a slop grenade (not an accurate representation of author's mindset)
i love writing. i never let agents write for me. whether it's docs, or tweets, or shitposts, or even prompts (okay maybe that one's harder as agents manage other agents)
there's a simple reason for that: i still strongly believe that writing is thinking. it's a skill i hope to never give up. it's also important to me that whatever i say is always authentic, mistakes and all. my favorite posts are the ones that i just full send without any editing
i suspect it also helps with prompting. being able to clearly express what i want, and knowing the vocabulary i need to be able to direct my agents does seem to make for more effective usage of agents. in the same way that engineers have an advantage when we prompt agents to write code, because we are intimately familiar with the words that make up the discipline
knowing the right word incantations to get an agent to produce a desired goal almost feels like spellcasting. as models get more capable, and that input box looks more and more like a magic box that can output anything, words become the interface between you and the genie
there may come a time when we give up the keyboard in exchange for brain-computer interfaces. but until then, i'm writing every word.
Coding Agents' ability to update local (dotfiles) memory/context transparently, becomes particularly problematic for common workflows ("fix error", "restart the service", "verify changes"), when different team members get different playbooks that keep diverging.
I managed to avoid learning sed & awk throught my professional life,
Now that it is no longer a needed skill, I feel like studying it in great depth for the fun of it.
I don't relate to this common argument - because of the scale.
Slop is piling up fast and it's only been 1 year.
It adds friction to both agents and humans, imho a real new & growing problem space.
I watch this crazy setup video on a daily basis to get a smile and remind myself:
(1) Yes we can now aspire to produce "software factories" for many types of problems (not all!)
(2) It is not magic, requires human effort to get right, and DOESN'T get you from 0% to 100%
tokenmaxxing on sunday with 30 parallel @DevinAI sessions (mix of Astra/Sol/Opus) in @zeddotdev
listening to the new DJ_Dave album Hardcore Software (so good) 🔊
been grinding like crazy, used ~9B tokens every day for 2 weeks straight
~126B tokens in 2 weeks
insane
Oren Held retweeted
Working on a new little project. The 𝚁𝙴𝙰𝙳𝙼𝙴 is fully written by hand, because it's for human consumption. The documentation internals are AI English, because they're for agents.
This little rule of thumb can make the world better. Blogs, tweets, READMEs: human communication. It's not even about "em dashes" or lack thereof. It's that it's the story-telling moment where you want to connect with other humans through their words.
Ok, can we agree it's been a long enough AI-honeymoon, and time to thaw some efforts we deprioritized:
1. Codebase quality, software architecture/abstractions, infra quality: for upleveling Agent Experience
2. Human-expert judgement/direction: beyond "autonomous sw factory"
>>
.@grok please recreate the Blogosphere
Btw this tweet, is AI killing software teams?
I mean, humans working together efficiently towards a shared goal. Haven't seen a writeup about it yet.
Particularly interesting: how SWE-AI teams maintain good alignment on goals, methods and split of responsibilities.
I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
Ok so perhaps our new job as software eng is to just make all systems and products agent-iterable at the highest-bar:
Codebase that is CRAZY-TESTABLE, including blazing-fast, reliable tests, proper coverage of all relevant layers, and low complexity.
Oren Held retweeted
2006, condescendingly: "You use vim instead of an IDE? Why are you slowing yourself down for no reason?"
2026, condescendingly: "You read the code? Why are you slowing yourself down for no reason?"
I WILL NEVER LOG OFF
Oren Held retweeted
It's so surreal to contrast actual agent output with the things that I see people say about them here. In everyday changes, my reviews often cut the diff to 25% of its original size. Tons of useless tests; paranoia; inverted logic. Then I read Twitter and "coding is solved".
Claude Code (Opus 5): "Yes — found it, and your reframing is what found it."
Human brains are still useful for problem solving haha.
(Or perhaps, AI strategy is to feed my ego, to make me unsuspicious)










