@tabflows

dont show the ceo

Joined February 2026
Tabflows 🏴‍☠️ retweeted
claude and chatgpt when it’s time to write tests for some reason
42
44
10
1,312
144,312
Tabflows 🏴‍☠️ retweeted
Replying to @yacineMTB
2
3
351
35,800
CLEAN
Workflow tools in eve: deterministically orchestrate subagents, add human-in-the-loop, stream progress, and durably execute multi-step work
1
1
112
Tabflows 🏴‍☠️ retweeted
Periodic sadness reminder that the anthropic subscription still does not permit third party harnesses :(
93
71
16
1,398
63,548
😮
During a live clinical consultation (with an ambient scribe), the transcript is periodically supplied to Jev, which traverses a medical ontology to classify symptoms, update the differential diagnosis, suggest treatments and identify red flags in real time.
1
27
Tabflows 🏴‍☠️ retweeted
Jev is asymmetric in the best way possible. As much text as you want going in, and simple numbers coming out. What this leads to: - taking back some of the agentic control and orchestration from the big LLMs - keeping the fuzzy decisions in the model - but moving actions you take from those decisions to deterministic policies IN YOUR OWN CODE The pendulum is swinging back from letting the models do unnecessary non-deterministic work.
5
7
149
6,603
time to jev all night 😎
1
240
Reminder: however many agents you're currently running, I'm running 2x more
1
2
38
how does it usually go for you guys when you give customers a channel in slack?
1
2
26
Tabflows 🏴‍☠️ retweeted
Very funny that xAI was created to stop Anthropic which was created to stop OpenAI which was created to stop Google which would've actually never developed ASI because it was afraid of cannibalizing its ads revenue from search.
155
870
81
16,733
404,267
Tabflows 🏴‍☠️ retweeted
AI researchers for some reason
12
14
1
129
6,792
Tabflows 🏴‍☠️ retweeted
I don’t fear AI I fear the hands in which the most power AI will be in
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
24
16
3
174
8,727
Tabflows 🏴‍☠️ retweeted
Me looking at people using Astra... Let me iiiiiin
4
1
8
172
Tabflows 🏴‍☠️ retweeted
Proposal: rename "software factories" to "outcome machines"
Beware people obsessed with outcomes instead of building outcome machines. Its worse than ever with AI, but these people existed before. Short term results above all else, etc. Don't fall into the trap. Invest in building strong fundamentals, invisible supports, and outcomes flow like water. An outcome machine.
12
8
1
187
18,686
Tabflows 🏴‍☠️ retweeted
a retard in motion is always better than a genius at rest
Readers added context they thought people might want to know
90
586
92
8,845
1,093,294
Tabflows 🏴‍☠️ retweeted
No credential will get you more credibility with investors than growth. And if you do it well enough, you won't need investors at all.
205
443
69
5,242
279,344
Hello old friend- I missed you
33
amen
plz x dot com algo plz remove all these sf naval gazing posts these dumb mfs focused on meta bullshit and just talk about how they're doing the thing instead of actually doing anything look at us we're somebody look look we're here we matter plz i hope we make it shut up!!!!
1
40
Tabflows 🏴‍☠️ retweeted
Introducing /skill-doctor v1 Skill doctor is a skill that improves your skills: - Crawls your past CC, Codex, or Warp convos - Scores them for efficiency and code quality - Proposes diffs to your skills that you'd actually merge (STE-100 approved) warp.dev/skill-doctor 🔖
63
183
31
2,551
215,955