Dan McAteer ✓

@daniel_mac8 · United States · joined 15 Oct 2013

I build AI agents for a living and write about it. Writing at https://t.co/ROXTvUfk75 · Writing @latentspacepod · Agentic Ops @ AnswerRocket

29 999Followers

4 602Following

36 026Posts total

694.8KViews on collected posts

Latest posts

Dan McAteer ✓@daniel_mac83 Sep

Sounds like consumers may get Astra today. 26.1K views · 250 likes · 5 reposts · 17 replies Open on X →

Dan McAteer ✓@daniel_mac83 Sep

The answer is no, apparently. 5.6K views · 87 likes · 0 reposts · 14 replies Open on X →

Dan McAteer ✓@daniel_mac83 Sep

GPT-6 Astra launch blog post returns a 404. What is going on here? https://t.co/yg9X3H8S2q 6.6K views · 45 likes · 0 reposts · 11 replies Open on X →

Dan McAteer ✓@daniel_mac83 Sep

Greg Brockman believes GPT-6 Astra is AGI. The press embargo has been lifted. Official release imminent. https://t.co/nZlaFutGBI 10.2K views · 99 likes · 3 reposts · 7 replies Open on X →

Dan McAteer ✓@daniel_mac83 Sep

Does anyone know what time the GPT-6 Astra launch starts? 114.3K views · 375 likes · 2 reposts · 43 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

GPT-6 Astra launch is tomorrow. You can feel it. It's staged in the OpenAI API. GPT-6 Astra returns a 404 but other non-existent model names return 400 errors according to @mrfanduu. Here's what I expect: 1. Human parity at computer use and superhuman speeds according to Sam h 4.2K views · 54 likes · 3 reposts · 8 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

@daniel_mac8 I have a slightly more complicated setup. I don't know if it would interest you but the way that I do it (and I know you could do it as quickly as I can tell you) is that I use Sol for hard problems as directed by Fable and deep analysis. I only use Luna for implemen 4.7K views · 7 likes · 0 reposts · 1 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

Use 'fable-advisor': https://t.co/pdnSpCbjyi 7.9K views · 54 likes · 2 reposts · 1 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

Yes, I will update to Astra tomorrow. 9.8K views · 25 likes · 0 reposts · 2 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

Fable 5.1 orchestrates GPT-5.6 Luna agents. Via the 'fable-advisor' plugin for Claude Code. 1. Fable 5.1 orchestrates 2. GPT-5.6 Luna implements 3. Fable 5.1 reviews Think of it like in-context distillation: give Luna the intelligence of Fable 5.1 at a fraction the cost. https 150.7K views · 1.1K likes · 54 reposts · 89 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

Does it make sense to do any work on your computer today when you're probably going to have Astra tomorrow? https://t.co/nAa6iiy58y 4.5K views · 78 likes · 2 reposts · 7 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

Astra uses "recurrent depth" reasoning, a more powerful but less legible form of reasoning. Fable 5.1 explains: https://t.co/aqo5XniIzu 17.5K views · 164 likes · 13 reposts · 10 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

@daniel_mac8 @RLanceMartin Is this only for API? Or sub too? macOS app? I’m trying the Fable all afternoon and holy guacamole it’s driving me nuts. Spinning in circles, bugs galore, it’s so bad. I can’t figure out where it’s gone off the rails for me. 6K views · 4 likes · 0 reposts · 1 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

Source: 11.1K views · 16 likes · 0 reposts · 1 replies Open on X →

Dan McAteer ✓@daniel_mac82 Sep

5 Fable 5.1 optimizations you can use *NOW*. 1. Set effort to 'low' 2. Run '/claude-api cost-optimize' 3. Run 'claude-api prompt-audit' 4. Change effort mid-conversation w/o cache hit 5. Update Fable 5.1 API config w/ 'claude-api migrate' From @RLanceMartin https://t.co/iM0G2FO 158.9K views · 1.3K likes · 81 reposts · 34 replies Open on X →

Dan McAteer ✓@daniel_mac81 Sep

some tips for Claude Fable 5.1 Try Fable 5.1 at low effort | Fable 5.1 at low effort is often competitive with Opus and Sonnet on $ / task while scoring higher. on CursorBench 3.2.0, Fable 5.1 at low effort is at parity w/ Fable 5 at high effort at a third of the cost. Prompt 156.9K views · 1.4K likes · 91 reposts · 70 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 views9 976this account924median for 10K–100K

Reach, %33.25%this account3.62%median for 10K–100K

Engagement, %0.89%this account1.52%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	9 976	924	10.8×
Reach (views ÷ followers)	33.25%	3.62%	9.19×
Engagement rate	0.89%	1.52%	0.59×

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

11.1K2 Sep

17.5K

4.5K

150.7K

9.8K

7.9K

4.7K

4.2K

114.3K3 Sep

10.2K

6.6K

5.6K

26.1K

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

0.15%2 Sep

0.08%

1.08%

1.95%

0.84%

0.29%

0.73%

0.17%

1.56%

0.37%3 Sep

1.08%

0.87%

1.80%

1.04%

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

What the audience does

Likes43.5%5 105 in total

Reposts2.2%256 in total

Replies2.7%316 in total

Quotes0.5%63 in total

Bookmarks51.0%5 983 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

Frequently asked questions about @daniel_mac8

How many followers does @daniel_mac8 have?

29 999 followers.

How many posts has @daniel_mac8 published?

36 026 posts.

How do posts by @daniel_mac8 perform?

Collected posts: 16. Views: 694 796. Likes: 5 105.