Advanced agentic systems. Products at kraliki.com. Work at verduona.com. Me at m-check1b.com

Prague
Pinned Tweet
What is happening!?
1
65
m-check1B retweeted
This is deeply disturbing: Anthropic secretly invited religious leaders to SF to advise them on AI safety, had them sign NDAs, but then primarily tried to convince them Claude has a soul & moral standing, all while wining & dining them to the max. 1/ tinyurl.com/preview/296b5z8z
454
1,542
9,296
4,283,631
m-check1B retweeted
Replying to @ai_for_success
Actually it was marketing campaign for grok 😅
1
1
10
1,461
m-check1B retweeted
Hard choices, easy life. Easy choices, hard life.
204
672
7,703
297,459
m-check1B retweeted
Burnout happens when you work too hard with not enough meaning. "He who has a why to live for can bear almost any how" — Nietzsche
251
957
11,532
646,277
m-check1B retweeted
It's funny that the only people who seemingly don't hate AI are computer programmers, and they are really the only ones who are getting completely replaced I guess programming really is that painful
204
121
3,657
125,212
m-check1B retweeted
Replying to @charles_maddock
my guess is the repo is technically better but nobody knows what happened
1
8
2,989
m-check1B retweeted
Replying to @theo
As Jeff Bezos said, "People who are right most of the time are people who change their minds often"
1
2
147
soooo how many claude subscriptions are you guys getting
34
5
300
13,469
m-check1B retweeted
imagine this happens lmao
125
127
6,148
130,347
m-check1B retweeted
Sonnet 5.5 Is Not A Very Good Model - spins on max mode - underperforms on agentic coding - slightly worse than Terra - stick either Sonnet 4.6 or DeepSeek Flash Anthropic should retire Sonnet and Haiku, release their big Model-2
59
10
283
29,776
m-check1B retweeted
btw I got a 6th Claude sub
229
9
1,856
103,629
m-check1B retweeted
OpenAI is Fucked Anthropic needs to start renting more compute for the users migration that's coming their way.
64
40
1,171
22,272
m-check1B retweeted
Anthropic was so mad about people distilling Fable that they decided to do it themselves with Opus 5.5
169
105
7,015
211,960
m-check1B retweeted
Bare MCP matcher never fires. Matcher "mcp__memory" looks finished. Official docs: that string is an exact match, and no tool is named that. Append .* — mcp__memory__.* navaigate.dev/writing/bare-m… skool.com/navaigate
1
1
17
m-check1B 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.
561
488
14,450
546,143
m-check1B retweeted
Replying to @theo
Like this 👇🏻
8
8
353
36,534
m-check1B retweeted
bro just dropped Gemini's system prompt
you are going to fail, so fail while daring greatly
123
463
12,859
573,200
m-check1B retweeted
Jev just solved doomscrolling. You pick a niche, Jev reads 3 days of posts and asks 8 questions each. It runs in ~2s for $0.007 😅 > removes bait and hidden ads > judges the text and like/reply/repost ratios Free, no signup, go try it then touch grass ↓🌲
83
70
1,700
178,725
m-check1B retweeted
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
426
678
10,863
3,884,765
m-check1B retweeted
At this point Bryan Johnson has more uptime than GitHub
108
103
4,450
136,543