tweetindex
EN

Steve Yegge ✓

@Steve_Yegge · Kirkland, WA · joined 06 Dec 2011

I've been in the industry for O(40) years and have written O(1M) LOC. I don't think I'll ever write O(another) line again, but I'll be launching more than ever.

48 416Followers
20Following
510Posts total
3.7MViews on collected posts

Latest posts

More Wheelhouse fun this week. https://t.co/QBzvKrzzgI
4.3K views · 29 likes · 0 reposts · 5 replies Open on X →
@Steve_Yegge Try Devin Desktop. We support major frontier models from OpenAI, Anthropic, SpaceXAI, Google, ThinkyMachines with one subscription. Also open models like GLM, Kimi, Deepseek. Also SWE-2 (our own model) which is currently free. We support other ~50 coding agents vi
7.4K views · 115 likes · 3 reposts · 18 replies Open on X →
@Steve_Yegge cursor projects + pstack. happy to send you credits to try https://t.co/ep5pyGwS0t https://t.co/nWAPoMCUda 29.2K views · 248 likes · 8 reposts · 37 replies Open on X →
@Steve_Yegge Hi 9.3K views · 135 likes · 0 reposts · 6 replies Open on X →
OK legit question for the AI-pilled, since there's no info on this anywhere. What are y'all mfs using for an agentic IDE, meaning, to multiplex 10-20 or more agents? Superlogical? Herdr? github/bb? Something else? I use Emacs, and I wouldn't wish it on you. But I want *something* 175.6K views · 715 likes · 16 reposts · 664 replies Open on X →
Introducing Projects, a new way of working in Cursor. Rather than creating a chat for every task, you work with a coordinator agent in a single, persistent thread. Like @bot, your agent is always on, proactively manages work with subagents, and improves over time. https://t.co/
1:33
2.9M views · 11.6K likes · 701 reposts · 677 replies Open on X →
More fun at the Wheelhouse factory... this was Fable 5. A few days later the factory train-wrecked itself and Fable 5.1 had to come in and fix it. Fable 5.1 torched about 30% of the whole thing. But it is fast now. https://t.co/7QQQzA3I36
11.4K views · 109 likes · 2 reposts · 5 replies Open on X →
@Steve_Yegge Any entity, capable of cause-and-effect reasoning, has a threshold on the length of the cause-and-effect chain. There may be a relationship between the length of that chain and IQ. Nevertheless, even the smartest AI agent has a limit. When the cause-and-effect chain 3.9K views · 47 likes · 2 reposts · 3 replies Open on X →
@Steve_Yegge i will just leave this here... again: 1.3K views · 9 likes · 0 reposts · 0 replies Open on X →
People ask me what it's like to be retired. I tell them, I don't have fuck you money, but I have bite me money. Somehow they always know exactly what I mean. 32.8K views · 250 likes · 6 reposts · 12 replies Open on X →
@Steve_Yegge People do this too! 1.7K views · 14 likes · 0 reposts · 0 replies Open on X →
All models, no matter how smart, will eventually build systems that they can no longer understand or maintain, if you let them. Fable 5 finally outbuilt itself, and flailed on me for a week. Fable 5.1 looks like it will fix it. For now. But you have to keep an iron grip on system 152.6K views · 964 likes · 77 reposts · 102 replies Open on X →
@Steve_Yegge I'm so happy that many people are calling out non-sensical and complicated AI terminology. I assumed I was just stupid. 6.6K views · 141 likes · 0 reposts · 3 replies Open on X →
@Steve_Yegge the way it’s not actually verbatim is *chefs kiss* 4.1K views · 160 likes · 0 reposts · 0 replies Open on X →
@Steve_Yegge later in the session: "avoiding doing [perfectly reasonable common sense thing] because of the hard user-imposed rule of [something I never knowingly agreed to]" 13.4K views · 1K likes · 17 reposts · 5 replies Open on X →
Something I noticed about working with Fable... https://t.co/PLaUjlZrJT
357.7K views · 7.4K likes · 503 reposts · 176 replies Open on X →
I am developing a formal theorem I call the Verification Complexity Barrier. In a nutshell, if a program has some components `n` that have connectivity factor of `k > 0` , then verification complexity increases superlinearly for each new component. Therefore the time required h
16.9K views · 81 likes · 11 reposts · 5 replies Open on X →

Against accounts of the same size

16 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views10 364this account924median for 10K–100K
Reach, %21.41%this account3.62%median for 10K–100K
Engagement, %1.01%this account1.52%median for 10K–100K
MetricThis accountMedian for 10K–100KRatio
Median views per post10 36492411.2×
Reach (views ÷ followers)21.41%3.62%5.91×
Engagement rate1.01%1.52%0.66×

Others in this range →   Compare with another account →   How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

4.1K11 Aug
6.6K
152.6K2 Sep
1.7K
32.8K3 Sep
1.3K
3.9K
11.4K7 Sep
2.9M10 Sep
175.6K11 Sep
9.3K
29.2K
7.4K12 Sep
4.3K15 Sep

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

3.92%11 Aug
2.19%
0.75%2 Sep
0.83%
0.82%3 Sep
0.71%
1.32%
1.02%7 Sep
0.45%10 Sep
0.79%11 Sep
1.51%
1.00%
1.84%12 Sep
0.79%15 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes66.4%23 104 in total
Reposts3.9%1 346 in total
Replies4.9%1 718 in total
Quotes0.4%139 in total
Bookmarks24.4%8 502 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Similar accounts