d1ock 🥷🏻

797 posts

d1ock 🥷🏻 banner
d1ock 🥷🏻

d1ock 🥷🏻

@0xdlock

CTO | Building good things @getNickAI

Stack Katılım Kasım 2021
629 Takip Edilen668 Takipçiler
d1ock 🥷🏻 retweetledi
NickAI
NickAI@getNickAI·
One AI Agent. One set of blind spots. One failure mode. 3 frontier LLMs. 1 BTC trading signal. 2-of-3 majority required. The Multi LLM Consensus template runs the same 48-hour BTC/USD price dataset through Claude, GPT and Gemini at the same time. Each model casts an independent vote: BULLISH, BEARISH, or NEUTRAL. A Python function node aggregates the votes, computes average confidence across the three models, and produces an agreement percentage. The signal only confirms on a 2-of-3 majority. A fourth model, Claude Opus, formats the full breakdown into a readable report: each model's signal, its confidence score, its reasoning, and the final consensus. It's consensus logic applied to frontier AI. Same principle behind investment committees and peer review, just running in parallel before your next BTC session. Try it for free now: getnick.ai
NickAI tweet media
English
3
1
2
149
Gir0fa
Gir0fa@gir0fa6723·
@0xdlock Can we get a link to the repo? Or is this closed source?
English
1
0
0
14
d1ock 🥷🏻
d1ock 🥷🏻@0xdlock·
GitHub UI is bad and slow. So I created my own!
d1ock 🥷🏻 tweet mediad1ock 🥷🏻 tweet media
English
1
0
2
213
d1ock 🥷🏻
d1ock 🥷🏻@0xdlock·
@sudox7 wait until you make it in assembly with direct syscalls only!
English
0
0
4
920
SudoX7
SudoX7@sudox7·
i made a web server in c using sockets, and honestly, i learned so much about how the web works
SudoX7 tweet media
English
57
119
1.7K
109.4K
s13k
s13k@s13k_·
@0xdlock Actually very beautiful
English
1
0
1
693
d1ock 🥷🏻
d1ock 🥷🏻@0xdlock·
Github if Riot designed it
d1ock 🥷🏻 tweet media
English
0
0
0
102
d1ock 🥷🏻
d1ock 🥷🏻@0xdlock·
github if supercell designed it
d1ock 🥷🏻 tweet media
English
0
1
2
140
Steve Ruiz
Steve Ruiz@steveruizok·
github if peak blizzard made it
Steve Ruiz tweet media
English
121
164
3.7K
172.3K
Tommy D. Rossi
Tommy D. Rossi@__morse·
GitHub if Linear designed it
Tommy D. Rossi tweet media
English
22
2
125
30.3K
Marcel
Marcel@marcelkargul·
$10k/mo for this level of design quality is charity
Marcel tweet media
English
26
11
268
33.7K
Max Musing
Max Musing@MaxMusing·
man, the new @linear review feature is actually good. I can finally work with 10k+ line diffs. still laggy in a few places but miles ahead of GitHub and Graphite.
Max Musing tweet media
English
14
2
327
27.6K
d1ock 🥷🏻
d1ock 🥷🏻@0xdlock·
Pull requests with proper visual hierarchy
d1ock 🥷🏻 tweet media
English
0
0
0
84
Wise
Wise@trikcode·
Great question, why did you move from Claude to Codex?
Wise tweet media
English
179
15
435
55.3K
Dear Men.
Dear Men.@Dea_rMen·
Probably this is the pinnacle of male happiness:
Dear Men. tweet media
English
36
378
4.7K
83.8K
Adib Hanna
Adib Hanna@adibhanna·
what AI tool are you using to come up with website designs?
English
3
0
1
670
Takuya 🐾 devaslife
Takuya 🐾 devaslife@inkdrop_app·
Reading Zed's source code to learn how to implement AI features with multiple AI providers for Inkdrop.. It reminds me of reading Atom Editor's codebase 10 years ago lol
Takuya 🐾 devaslife tweet media
English
15
9
483
22.8K
Archive
Archive@ArchiveExplorer·
This guy works at coinbase. in his spare time he built the largest open dataset for polymarket and kalshi 72,100,000 trades. 7,680,000 markets. open source - figured out who actually makes money on prediction markets - wrote a research paper with the math to prove it - 3,100 stars on github just for that also built heimdall-rs - rust toolkit for evm bytecode analysis. 1,500 stars. serious dev 3,008 contributions in the last year while everyone's posting takes about polymarket - he's building the infrastructure underneath it → github.com/Jon-Becker like + bookmark. you'll need this when you build your first polymarket bot
self.dll@seelffff

x.com/i/article/2049…

English
29
89
1K
118.2K