tweetindex
EN

murat 🍥 ✓

@mayfer · Vancouver, BC · joined 08 Mar 2008

20 151Followers
9 265Following
16 036Posts total
266KViews on collected posts

Latest posts

@mayfer I would 313 views · 16 likes · 0 reposts · 0 replies Open on X →
@mayfer honestly that would be such a vibe. like all those hours of reading activations finally paying off. makes you wonder what else were missing just because we dont look close enough. 49 views · 0 likes · 0 reposts · 0 replies Open on X →
@mayfer What is auto interp? 110 views · 0 likes · 0 reposts · 1 replies Open on X →
i wouldn't be surprised if what pulled astra ahead in capability and alignment was a bunch of autointerp 2.7K views · 17 likes · 0 reposts · 5 replies Open on X →
yea 408 views · 0 likes · 0 reposts · 0 replies Open on X →
a ha 680 views · 2 likes · 1 reposts · 1 replies Open on X →
I built pi-posthorse, a Pi extension inspired by Codex's new approach to context management. Instead of relying on compaction, agents can inspect context usage, reset their context window, write durable notes, and search their full session history. https://t.co/6woFQYB1l4 120.4K views · 870 likes · 41 reposts · 28 replies Open on X →
from Astra blog - Codex compaction is already great, never think about it, have multi-week threads turns out avoiding destructive (unrecoverable) summarization actions + letting a very smart model search over previous context…just works scaling + improving general search https:
123.5K views · 874 likes · 37 reposts · 36 replies Open on X →
@mayfer kv cache and your purse will say no 3.1K views · 30 likes · 0 reposts · 2 replies Open on X →
if i had to guess, context compaction will be replaced with each turn being a completely fresh request that agentically reads parts of the session history that it finds relevant via old school greps, summary line items, vector searches and so on @badlogicgames wdyt 10.4K views · 63 likes · 0 reposts · 19 replies Open on X →
cross-platform development is baby games in comparison to cross-desktop-manager compatibility across all linux flavors. absolute final boss of vibecoding 1.5K views · 11 likes · 0 reposts · 1 replies Open on X →
ray kurzweil suspiciously quiet on when he expects the first robot to successfully change a duvet cover 1.8K views · 29 likes · 2 reposts · 1 replies Open on X →
simpler times https://t.co/Hwn9ylNWjA
1K views · 10 likes · 0 reposts · 1 replies Open on X →

Against accounts of the same size

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

Median views1 521this account924median for 10K–100K
Reach, %7.55%this account3.62%median for 10K–100K
Engagement, %0.83%this account1.52%median for 10K–100K
MetricThis accountMedian for 10K–100KRatio
Median views per post1 5219241.65×
Reach (views ÷ followers)7.55%3.62%2.09×
Engagement rate0.83%1.52%0.55×

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

1K1 Sep
1.8K
1.5K3 Sep
10.4K
3.1K
123.5K4 Sep
120.4K
680
408
2.7K7 Sep
110
49
313

Last 13 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.06%1 Sep
1.82%
0.85%3 Sep
0.80%
1.03%
0.78%4 Sep
0.79%
0.59%
0.00%
0.83%7 Sep
0.91%
0.00%
5.11%

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

What the audience does

Likes73.9%1 922 in total
Reposts3.1%81 in total
Replies3.7%95 in total
Quotes1.1%28 in total
Bookmarks18.3%475 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