Louie Bacaj ✓

@LBacaj · New York City · joined 08 May 2009

Engineer turned Entrepreneur, turned Engineer, and the cycle continues.

28 520Followers

1 680Following

20 171Posts total

32.9KViews on collected posts

Latest posts

Louie Bacaj ✓@LBacaj5 Sep

On the left (first) Claude Fable 5.1 On the right (second) GPT6 Astra Same prompt, with access to the same assets. https://t.co/qTgefCLsGX

0:46

1.9K views · 9 likes · 0 reposts · 2 replies Open on X →

Louie Bacaj ✓@LBacaj2 Sep

@LBacaj We're all in the same boat, I posted multiple times about this. Expecting them to fix this within 24h and reset limits one more time @ClaudeDevs otherwise, I am taking my money to @OpenAIDevs 854 views · 8 likes · 0 reposts · 1 replies Open on X →

Louie Bacaj ✓@LBacaj2 Sep

@LBacaj Ultra mode usually isn’t a great fit for either Codex or Claude. A better approach is to use xhigh with a custom sub-agent workflow and let different agents handle different parts of the task. 875 views · 7 likes · 0 reposts · 1 replies Open on X →

Louie Bacaj ✓@LBacaj2 Sep

@LBacaj 116 agents ? and you're surprised it burnt your tokens? bruh 906 views · 11 likes · 0 reposts · 1 replies Open on X →

Louie Bacaj ✓@LBacaj2 Sep

This new Fable 5.1 model by anthropic is a joke. A single ultracode session consumed 42% of the weekly limit. Sub agents keep failing, for no reason. Then hits session limits on this single run retrying the sub-agents. Basically 42% of the weeks $200/month burned to failure ht

21.4K views · 317 likes · 15 reposts · 62 replies Open on X →

Louie Bacaj ✓@LBacaj29 Aug

Sometimes it feels strange to make things with AI. Feels like being an imposter, like “you didn’t really make that, AI did.” But then I remember I used to make a lot of this same stuff before AI, just a lot slower. And I feel good about these new tools again. 1.6K views · 29 likes · 2 reposts · 6 replies Open on X →

Louie Bacaj ✓@LBacaj28 Aug

It's insane that fable sends you back to opus 4.8 if you ask it to harden your own websites & apps from attackers. 1.5K views · 17 likes · 3 reposts · 0 replies Open on X →

Louie Bacaj ✓@LBacaj22 Aug

@LBacaj Anything you’ve done for yourself that you love specifically? (Seconding @PSaezT - most useful have been personal tools.) 63 views · 2 likes · 0 reposts · 0 replies Open on X →

Louie Bacaj ✓@LBacaj22 Aug

@LBacaj Most of the tools I've built so far are internal and I feel are so valuable. I've use them a bunch and they've either enabled me to do more stuff or do the same things I do in less time. I'm sure that these are the tools that could be marketed later once they've been test 55 views · 3 likes · 0 reposts · 0 replies Open on X →

Louie Bacaj ✓@LBacaj22 Aug

@LBacaj I’ve been building with AI for the past 18 months. A lot of it has been shit, a lot of it has been meh, some has been ok, very little has been exceptional. AI won’t change the ratio of good ideas to bad ideas. 140 views · 3 likes · 0 reposts · 2 replies Open on X →

Louie Bacaj ✓@LBacaj22 Aug

Something interesting about the age of AI, is the realization that most ideas are crap. Because now you can build basically anything. And people do. But the vast majority of it ppl either do not want, adds no value, or cannot be marketed. 3.8K views · 85 likes · 4 reposts · 17 replies Open on X →

Against accounts of the same size

11 posts from the last 90 days, next to the 10K–100K follower range. right around the median for its follower range.

Median views906this account924median for 10K–100K

Reach, %3.18%this account3.62%median for 10K–100K

Engagement, %1.89%this account1.52%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	906	924	0.98×
Reach (views ÷ followers)	3.18%	3.62%	0.88×
Engagement rate	1.89%	1.52%	1.24×

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

3.8K22 Aug

140

1.5K28 Aug

1.6K29 Aug

21.4K2 Sep

906

875

854

1.9K5 Sep

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

2.85%22 Aug

3.57%

5.45%

3.17%

1.32%28 Aug

2.38%29 Aug

1.89%2 Sep

1.32%

0.91%

1.05%

0.59%5 Sep

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

What the audience does

Likes77.6%491 in total

Reposts3.8%24 in total

Replies14.5%92 in total

Quotes1.6%10 in total

Bookmarks2.5%16 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.

Latest posts

Against accounts of the same size

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Similar accounts