codemilli (@codemilli) header
codemilli (@codemilli) profile picture

✽ Spelunking...

Ethereum
Joined December 2012
Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)Photo by codemilli (@codemilli)
Daily CSF
1
9
4,882
Opus 5.5 medium autocompact 256k is GOAT
1
20
codemilli retweeted
it's shocking that software engineering has transitioned to 100% AI written in such a short time. it's more shocking that somehow we, the SWEs, are all just continuing on as if nothing happened. It writes C++ better than I ever could, but the problem of making sure it works didn't magically disappear. we are just shipping enormously more volume at higher quality.
331
668
225
11,135
1,850,788
codemilli retweeted
At yesterday's Apple Intelligence Group Lab livestream, many of you had questions about Apple Foundation Models context size. We recently published a doc Article with more details. developer.apple.com/document… You can also see it on the terminal using the fm cli. Also, fun fact: You can start a Chat Completions API server using the on-device model using fm serve
4
19
1
235
17,820
The web rewrite is working. On a slow connection, the old X web took more than 22 seconds to show the first post on a profile. The new X web does it in 2.7 seconds. Here's how we did it, and how we're rolling it out one country at a time. blog.x.com/en/engineering/re…
290
363
164
5,058
1,062,691
codemilli retweeted
IPX is bringing minicoin payments to @LINEFRIENDSinfo stores! in both online and offline stores, the rollout is targeting the first half of 2027 lenini is already practicing accepting your MINI at the register! official announcement from IPX: markets.businessinsider.com/…
11
9
2
64
8,638
One of the most valuable technical skills is explaining complex work clearly.
96
481
54
4,475
146,954
This is HUGE
Turn an idea into a working onchain app with Arc Studio. Describe what you want to build, then generate, review, test, and export the code with your own tools and infrastructure. → Smart contracts → Frontend UI → Tests → Docs → Deployment workflows studio.arc.io/
88
codemilli retweeted
volume does matter look, i get it. if you were an engineer before agents came along, you're rightfully skeptical about lines of code and number of PRs being used as a metric for any kind of productivity. and i agree! or at least, i used to. for ease of explanation i will talk about this from the perspective as being an engineer on a large team of at least 50. volume didn't matter before because we focused on impact. you could have high impact even with a few PRs: for example you could make a one line config change and save the company millions of dollars. but before agents, the times where i saw volume come into the conversation were for the outliers. on the negative end you might have someone who is struggling to perform, on the other end you might have someone who was a "coding machine" archetype. a coding machine was someone who could just lock themselves in a room and emerge with a stack of PRs that solve a huge number of problems. so volume did matter, but only at the tail ends of the distribution, and combined with impact. if you've ever worked at a large tech company before, you'll get what i mean. the thing about agents is that big tech co problems are now small-medium co problems as well. how do agents change this calculus? well, everyone now has the ability to become a coding machine. you have incredibly capable frontier models that can write code better than any of us, at a rate much faster than we can. in this world, if you're still producing the same number of PRs as before, why wouldn't you pause to wonder why you're not being more productive? alien intelligence is here, and yet you can't outship a human coding machine? this brings me back to why i keep talking about trust (teapawt.org/poteto/status/21020504…). if you haven't put in the work to trust your agent's output, it is very difficult to scale up your productivity. and yes, this approach does require more tokens, but i think about this in terms of cost per intelligence. before agents, this cost was very high - you needed to hire many software engineers with high 6 figure salaries to do the work. tokens are still expensive today, but are likely to get cheaper over time (teapawt.org/theo/status/2107924138…) factoring in the cost of intelligence. what looks exorbitant today will likely be affordable in 6 moths to a year. a single engineer with agents can do the work of tens if not hundreds of engineers, at a fraction of the cost. the reality that i don't think has hit yet is that job of the software engineer has truly changed. our job is not merely to produce software any longer (well tbh it was never only about the code, but bear with me for the sake of the explanation), but the machine that writes the software. this idea of a software factory, or a Michelin kitchen as i like to call it, is still a topic of research. and it's the type of stuff i like to share, not to flex, but to show you what's possible when you put a lot of rigor into using agents at scale
Can someone help me understand how shipping 100s PRs a day makes sense? Why do you need to ship so many PRs in the first place? I might just not be AI-pilled enough to understand the need for it yet, so I’m genuinely trying to understand it.
224
246
87
4,046
385,461
ㅇㅇ
working at a higher level of abstraction has always required understanding the lower level ones, I don't think coding agents changes this
1
61
Except oai one
Important note regarding Grok @Bot: Going forward, @SpaceX will use the best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno and other leading APIs. Whatever is most likely to give you the best outcome.
42
codemilli retweeted
working at a higher level of abstraction has always required understanding the lower level ones, I don't think coding agents changes this
298
415
89
5,605
362,765
😌
The way Steve taught us to care about every detail, every experience, every person, still guides our work today. Forever grateful.
1
37
codemilli retweeted
No more AI SI It’s better
19,947
12,602
5,305
136,237
18,188,402
Grok Bot has such great UI/UX that it’s hard to imagine how it could get any better.
Grok bot is 100x better UI experience than dots.
48
codemilli retweeted
My god this is such a good speech that every SWE needs to hear. You know what? Every person should hear it Keep the happy memories, eyes on the reality, be excited about the future. That’s the best that anyone can do
374
2,072
658
15,838
3,706,270
codemilli retweeted
GPT 6 Sol vs Opus 5.5 in a nutshell :/
284
90
63
8,478
1,556,369
codemilli retweeted
One week on Arc Mainnet. 624M USDC in circulation. $6.8B USDC transferred. Day one was just the beginning.
280
268
116
1,406
134,296
codemilli retweeted
Anthropic has no small models that are worth using right now. OpenAI has no large models that are worth using right now. Google has no models that are worth using right now.
556
483
142
14,525
807,942