Clarke Stevens (@darkestevens) header
Clarke Stevens (@darkestevens) profile picture

Persistent + kind + curious. I build cool tech during the day, I play keys and cards at night.

Greenville, SC
Joined November 2010
Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)Photo by Clarke Stevens (@darkestevens)
Should we call it a meat cute? Once a month I grill 3+ lbs of meat and we share with friends from left to right: Angus steaks, garlic parm chicken wings, bourbon-glazed shark, butterflied chicken breast
I heard that we are sharing our meats for the Japanese. Here's a couple things I've grilled: Copycat In-N-Out double cheeseburgers, brisket, a smoked Christmas goose, and some steaks.
1
2
276
Clarke Stevens retweeted
something that keeps bothering me is how some people see slop as something that is happening to them, like they're some kind of helpless bystander powerless to do anything about it excuse me but you are a software engineer, you literally learned how to make sand think and make computers do your bidding?! and now you can't do anything about it? please the 2 things you should know to cut through all the noise: 1. you need to give your agent a way to verify its own work (i just posted about this so won't rehash) 2. your codebase is memory the 2nd is not new either, we have always had lint rules, compilers with good diagnostics and strong type systems, LSPs, etc to help us write better code. there is no difference when agents write the code instead, you just need more of them, and stronger ones. forget rules and skills. you can add those later. yes, your codebase is a form of memory to agents! agents love extending what already exists. so every nit and every annoyance you've ever seen, every mistake and bad pattern you observe from agents, needs to turn into a constraint, or the agents will just keep repeating those same mistakes like a virus in your code. then you keep observing and repeating this process until your codebase is locked down enough that even agents with little context can one shot a high quality PR. an even better direction is to refactor/rewrite your code such that agent anti-patterns become categorically impossible. use type systems to your advantage, use libraries/frameworks that reduce the architectural search space, or heck, create your own framework like we did for grok bot and design high quality primitives and well thought out APIs
the slop conversation is so one sided, it's not just that you can produce more code you can also observe, debug, and refactor more code even if the code is slop you have such good tools to deal with it. even if you write code manually, it's still 100x easier to maintain it
232
339
103
4,625
332,647
Clarke Stevens retweeted
Some of you never had to make sure the boat didn’t hit the dock when you were little and it shows.
28
8
2
234
55,137
nobody bats an eye if you eat doritos and drink beer but the second you eat steak and get lots of sunlight people tell you you're killing yourself clown world
38
235
9
3,162
52,196
If you were a single issue voter, what would your single issue be?
2%Legalize drugs
36%End wars
12%COVID Accountability
50%Reduce spending
9,016 votes • Final results
635
57
31
355
35,813
Clarke Stevens retweeted
Every backend service should have a /feedback endpoint. Agents are quickly becoming the heaviest users of most APIs. When one hits a missing feature or a bug, it should be able to say so right there, in a structured way. If the request makes sense, another agent drafts the PR and a human approves it. Software that improves itself based on what its users actually tried to do speeds up recursive self improvement.
298
173
112
2,362
247,293
opus 4.5 was my breaking point. haven't looked back
I used to be a hard-core fan of Claude since forever, never switch to another API or LLM since Opus 4.8 came out Until this August, whatever they did, I haven't been screaming and annoyed at it's work like this before and moved completely over to OpenAI + Grok I thought I was going crazy, but apparently they pulled the same shit they did back earlier this year with regression
97
Clarke Stevens retweeted
Congress has worked so few hours this year that lawmakers wouldn't even meet the Medicaid work requirements they passed.
VOTES THURSDAY CANCELED today is the houses last day until after Election Day.
53
6,858
97
36,305
525,899
just discovered @cursor_ai had profiles. not bad for a people manager right?
33
If you're not using git worktrees with your agents, you're about three months too late to the party
41
Clarke Stevens retweeted
I don’t know why people keep saying this. I just point the agents at a folder that has 100 or so repos and it goes to town. I often don’t even have the repo I need pulled down and it’ll go clone it to do what I need. Maybe this was true in 2024 and people just assumed it would be true forever.
Monorepo is going to be the most optimal setup to properly work with AI given all the context is in one codebase
46
9
3
220
25,871
Clarke Stevens retweeted
men are simple. they need a project, a woman who appreciates them and red meat. stop overcomplicating things.
37
42
17
442
23,445
Clarke Stevens retweeted
If a toddler offers u an unwrapped piece of candy from his sticky hand, that’s a sign of great respect in their culture
54
1,068
35
17,709
374,865
Clarke Stevens retweeted
If you want to hate America watch the news If you want to love America visit the people
94
639
55
11,071
592,054
Clarke Stevens retweeted
Replying to @_ARahim_ @bcherny
only boomers fix typos in prompts. llms perfectly understand you even if you mistype.
345
189
96
5,229
164,298
Since I have to attend this corporate training, you do too 🧵
1
25
Should I just link to this thread in the survey?
1
5