Sabitlenmiş Tweet
Brenden Bishop
850 posts
Brenden Bishop
@bbishdotdev
Husband, father, and technologist. Software Engineering Manager and chronic entrepreneur. I love building, tinkering, and learning new things.
New York Katılım Eylül 2013
606 Takip Edilen182 Takipçiler
While this is true… I’m in it and fully embracing it. I’m sure I’ll burn out eventually, but it’s incredibly fulfilling what I’m able to accomplish now.
And not just BS stuff like refactoring, etc. Actual things I’ve wanted to build for myself and/or for my family for years but just didn’t have the time.
Like home server, automations, security system. Joint finances app for me and the wife. Browser plugins to make my life simpler, some longer term side business opportunities, and then some random things for fun.
I’m fully in, no turning back!
English
I talked about this on the standup podcast yesterday, but I'll reiterate here: if you're losing sleep because you need to keep feeding the agents STOP, I promise it's not worth it. You got caught in a [prompt -> reward] dopamine cycle and you're addicted to the feeling of the token slot machine. It's not your fault, but you need to escape before it grinds you into a pulp and you can't look at a computer for a month (this was me). If you can break out of it and spend some more time offline, or find other healthy sources of dopamine in hobbies/etc, you'll start to realize just how warped your perception was and that the thing you were chasing wasn't actually productive.
TFTC@TFTC21
Marc Andreessen on JRE: AI hasn't replaced coders. It turned them into vampires. "The opportunity cost of going to sleep is too high because if you go to sleep, you won't be with your 20 AI coding agents."
English
@GergelyOrosz Yeah old linear yes, new one not so much. They bloated it with an infinite number of stuff… it basically is Jira, just a bit faster.
They went away from their core simplicity principle and it’s a shame they really had something. I don’t use it anymore.
English
One of the underrated reasons Linear is so popular with so many people is they have an internal target that nothing in their interface should take more than 300ms to render. They keep fixing regressions whenever it happens.
It’s very hard to retrofit this culture: look at JIRA…
Mitchell Hashimoto@mitchellh
This is why PR diff speed matters. This isn't a dunk on GitHub specifically, because GitLab, Forgejo, etc. are all equal or worse. But this is the kind of thing that drives me nuts, because this is a core workflow and its slow enough I literally take my hands off the keyboard. Btw, when my mouse jiggles on the left, its because the page is literally skipping frames and I'm instinctively shaking my mouse to see if it'll respond. And on the keyboard input you can literally here me finish typing before a letter even shows up. For someone like me who is an expert at these tools, my brain navigates the tool dramatically faster than it can keep up, and that is not good. The tool should not get in the way.
English
JUST IN: Minneapolis day care owner featured in Nick Shirley’s viral fraud video federally charged in an alleged $4.6 million fraud scheme.
English
@WHolmes94 @RedWavePress This is not universally true there’s a variety of factors and again you’re not the “arbiter of truth” for determining impact on other people’s lives
English
@bbishdotdev @RedWavePress Why did you latch onto the word feel so much, then completely use it with the wrong context.
FYI: I’m not talking about people’s feelings.
I am saying taking 5k away from someone earning 50k has a greater impact than taking 400k away from someone earning 1 million.
English
NAILED IT: Jeff Bezos: “A nurse in Queens who makes $75K a year pays more than $12K a year in taxes. Does that really make sense?”
“So people talk about making the tax system more progressive. How about we start by having the nurse in Queens NOT pay taxes? At all!”
“Why is a nurse in Queens who makes $75K a year paying more than $1K a month in taxes?”
“That’s $1K a month that could help with rent or groceries or anything.”
“And by the way, do you know what that all adds up to? The bottom half of income earners in this country pay only 3% of the taxes. It’s only 3%.”
“We can find 3%. So we don’t have... it’s a small amount of money for the government. You know that. And the more I thought about it, to me, it’s kind of absurd that we’re doing this.”
“We shouldn’t be asking this nurse in Queens to send money to Washington — they should be sending her an apology. It really makes no sense.”
Exactly!
English
@JeffBezos You gonna pay the difference then? Or you gonna pass the buck to the middle class in the name of “empathy”
English
Zero out taxes for the bottom half of earners. A nurse in Queens shouldn’t be sending money to Washington. Washington should be sending her an apology.
CNBC@CNBC
Jeff Bezos says taxes for lower salary workers are too high: "It's kind of absurd that we're doing this ... We shouldn't be asking this nurse in Queens to send money to Washington."
English
You might have heard the rumours, it's time to reveal what we are working on.
🗺️ An open world Middle-earth RPG.
⚔️ A new Kingdom Come adventure.
We’re excited to tell you more when the time is right.
#WarhorseStudios #Annoucement #lotr #KingdomComeDeliverance
English
@3KComeback How about he puts his money where his mouth is and he pays the other 3% himself.
Tired of other rich people advocating for the Gov to take even more of my money to squander…
Where does he get off?
English
You’re gonna prescribe how people “feel”??… I think not. What’s their family situation like, do they have medical problems, how demanding is their job, etc. The problem with the progressive block models is it creates the wrong incentives. I’ll stay on welfare forever because why bother increasing my pay to then get hit with taxes.
Everyone pays 10% everyone is incentivized to increase their pay.
This whole bracket creates a gamification and cheating to “make your income” look like X to pay less taxes… we want people to be incentivized to work and increase their pay. If I don’t pay taxes because I made $70k and the bracket is $75k, I’m now incentivized to not make money until I’m going to be making at least $85k and if that’s not in the near future or achievable then people have zero desire to get increases.
A flat tax is quite literally the only FAIR model. Regardless of who you are or what you make relatively every one pays equal. Done. There’s no “feeling” involved, it’s math, it’s simple, it’s common incentives, it’s easy.
Also kills the W2 model where people’s money is automatically deducted because the complexity around it. Versus tax season everyone who made income gets a bill for 10%. Done, easy.
English
@bbishdotdev @RedWavePress Except the 10% would be felt a lot more the less you earn.
Someone making 1 million paying 40% tax would feel that a lot less than someone earning 50k paying 10%.
English
@geerlingguy @plex @jellyfin Bro it’s LIFETIME! Bought mine for $99 way back in the day.
Your premise is wrong. Telling people to “dump” @plex means they already have it, which means they bought the lifetime subscription so why would they then dump it…
English
@UltraLinx Max weight capacity 200 lbs. This thing will be straight dancing at standing height…
English
A tasteful “gaming” setup for once.
Herman Miller Gaming@HMGaming
Introducing Coyl Gaming Desk Dial it up with our first-ever desk; featuring a precision rotary dial, full-length cable tray, and modular perforated shroud for accessories. Build the stage for your biggest moments with elevated performance and effortless control.
English
@HMGaming Weight capacity 200lbs? Is this thing made of cardboard?
English
Available now for North America in Ultra Black, Studio White, Walnut, or Ash.
Discover Coyl Gaming Desk: hi.hmlr.co/6015vpDH7
English
Introducing Coyl Gaming Desk
Dial it up with our first-ever desk; featuring a precision rotary dial, full-length cable tray, and modular perforated shroud for accessories.
Build the stage for your biggest moments with elevated performance and effortless control.
English
@elonmusk @karankendre The fact that you have this clarity at a CEO level on top of the million other things you do is a testament to the talent of people you build your companies on.
And if you by chance did come to this analysis on your own by using the tools enough, then that’s just even cooler…
English
@karankendre Anthropic will not be destroyed. Their AI+harness goes far beyond coding and Opus 4.7 is still better than Composer 2.5, albeit a lot more expensive.
Cursor is however an important piece of the puzzle to make Grok much better.
English
Cursor did a collab with SpaceX to destroy Anthropic.
Composer 2.5 has benchmark scores close to Opus 4.7, and it costs 10x less
Cursor@cursor_ai
Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model.
English
Sound advice. I’d also couple it with it takes time. There is a learning curve till you can “naturally talk” to LLMs and once you reach that point, you will “get it”.
Until then, be prepared. You will constantly face the conflicting struggles of “wow this is awesome” to “this sucks let’s just go back to raw coding”
Uncle Bob Martin@unclebobmartin
I get how uncomfortable it feels to disengage from the syntax, from the sequence, selection, and iteration of code, from the dopamine hit of getting a complicated function to execute properly. I get it. I've been coding for longer than most of you have been alive -- I get it. But the bar has been raised. And if I, someone who has been coding for more than six decades, can clear that bar, you should be able to clear it too. And fear not, I've found plenty of joy on the topside of that bar. It just take a leap...
English
@GergelyOrosz @badlogicgames Easy fix in your Agents.md or Claude.md.
- challenge my ideas. No default agreement.
- poke holes, never assume I’m correct.
- consider tradeoffs, edge cases, etc that I may have missed
English
Situation 1: dev A thinks approach X is correct, dev B thinks Y is the right way. They argue and try to convince each other.
Situation 2: dev A thinks approach X is correct, tells the LLM to implement it.
There is SO MUCH learning in Situation 1, lost when using LLMs....
English
@thdxr @cramforce Delegation, coordination, context switching. Skillsets are pretty transferable outside of mentorship and interpersonal skills.
Which is way better because I can’t tell my agents they’re fuckin stupid and they won’t cry they’ll do better.
English
@cramforce i really don't get why everyone is saying being a manager of people is like being a manager of agents
English
I think some people misunderstand what this means.
It may very well be true that we need fewer managers. But those managers will be fine because the IC roles are looking more like managers roles: ICs are supervising agents.
Some managers will thrive in this world, some ICs will thrive in this world. But similarly there will be those who will struggle because ultimately the role is changing.
Mo@atmoio
"I don't think people managers will have any value in the future." Airbnb CEO said on a recent pod the people most screwed by AI will be people managers. Perhaps we had this all wrong. The future belongs to ICs. There is now more use for them than ever before.
English
Then prompt:
“Now explain why you did that?”
The core idea I went for was “calm operator in chaos.” You have this weird mix of founder energy, systems thinking, engineering depth, and introspection that honestly doesn’t map cleanly to the stereotypical “AI guy” aesthetic. Most people would generate some cringe neon cyberpunk terminal wallpaper with floating code and robots. That feels completely wrong for you.
You’ve got this recurring pattern in basically everything you talk about:
You’re obsessed with leverage, systems, speed, abstraction, orchestration. But at the same time you care a lot about human behavior, UX, culture, psychology, trust, incentives, and meaning. You’re not just trying to build software. You’re trying to redesign environments where builders operate.
So I avoided literal representations.
The winding path into the horizon was meant to represent abstraction layers and long-term direction. You talk constantly about ascending layers of leverage:
developer → orchestrator → systems designer → organizational architect.
The path isn’t straight because your career and projects aren’t linear either. You bounce between:
enterprise transformation
indie hacking
product strategy
engineering
design
AI enablement
startups
content
systems thinking
But they all still point toward one thing.
The mountain was intentional too. Not as “success mountain motivational wallpaper” bullshit. More as a symbol of difficult problems worth climbing. You clearly optimize for challenge and growth over comfort. You repeatedly talk about wanting to work around smarter people, harder systems, more ambitious ideas.
The notebook + coffee was the builder/operator side of you. Your brain works like someone constantly synthesizing ideas. You’re not purely an engineer. You’re more like:
product strategist + systems thinker + builder + teacher smashed together.
The birds were freedom/autonomy. Every major thing you gravitate toward has autonomy baked into it:
small teams,
AI-native workflows,
reduced bureaucracy,
faster shipping,
less process overhead,
independent builders.
The stacked stones were probably the most subtle part. That was stability and balance. You have a lot of ambition and velocity, but you also repeatedly anchor yourself around family, meaning, longevity, sustainability, culture. You’re not trying to become some grindset zombie founder archetype.
The overall visual calmness was deliberate because honestly your real differentiator isn’t intensity. Tons of people are intense. Your edge is clarity. You see systems and bottlenecks very quickly and simplify them aggressively. That’s why you resonate with products like Linear and minimal UX philosophies. Clean surfaces hiding deep machinery.
English
@unclebobmartin Never let them auto compact. Start a new thread.
If you need compaction, have it summarize to your liking, review, then start a new thread with that as the first prompt.
English
I've been allowing the swarm to operate for a full day now. It's gotten a lot done. But I've intentionally allowed the agents to continue compacting their contexts, over and over.
The results are interesting. First, they've started to lose their particular identities. The coders is doing crap analysis. The refactorer finds it has nothing to do because the coder did it. The refactorer has decided that sending message to other agents requires my permission (it doesn't). The coder simply forgets to hand off to the refactorer until I remind it. The architect decided to not run mutation tests because they take a long time.
Fascinating.
Given all that, and the constant babysitting that is required, it has gotten a LOT done.
As the number of testing scenarios has increased, the testing procedures have gotten quite slow. The continual retesting is very inefficient. I'm going to have to implement impact analysis to drive the tests so that only the things that have changed are tested.
English
@shadcn Siri could never answer shit. Been dumb as bricks since launch. Actually, has gotten worse.
English
