David

544 posts

David banner
David

David

@dd_tch

Off The Edge of The Earth and Into Forever, Forever. AI and Web3 positive

New York 参加日 Aralık 2009
121 フォロー中428 フォロワー
David
David@dd_tch·
Finally number of my repositories on GH become sexy
David tweet media
English
0
0
1
33
David
David@dd_tch·
@ellie_huxtable its awesome! waiting updates! god swear Atuin became for me first tool I install on my vps, servers, local machines, vm's etc
English
1
0
2
49
Ellie Huxtable
Ellie Huxtable@ellie_huxtable·
working on rendering our inline TUIs on top of terminal content, without first clearing space or using alt screen
English
15
1
148
9.2K
David
David@dd_tch·
vibe coded personal task tracker with calendar, added mcp to it and voice calls with @retellai. It's really cool when agent actually calls you instead of silent notifications we never pay attention to. github.com/ddtch/lite-task check it out and grab if you want
David tweet media
English
0
0
0
56
David
David@dd_tch·
YT is down I bet it’s dns again
English
0
0
0
38
Gunnar Gray
Gunnar Gray@gunnargray·
Unicode braille animations ⠿
Français
74
119
2.8K
234.2K
David
David@dd_tch·
Ok ppl, are we going from mcp to A2A protocol now?
English
0
0
1
26
David
David@dd_tch·
literally spent 45 minutes today to set up own instance of @langfuse so easy so good
English
0
0
1
40
nader dabit
nader dabit@dabit3·
Something I wanted to see if Claude Opus 4.5 could do: clone a fully functional Billion $ SAAS product and make it at least 100x cheaper. The first product that came to mind was TypeForm because it's very popular, very expensive, and in theory, very simple. The result is OpenForm: a polished + functional and Open Source Typeform clone at ~100x less cost, that can be setup and deployed in ~15 minutes. The agent building this ran for ~35 minutes. Here are the details, technique, and the code:
English
328
394
7K
1.8M
David
David@dd_tch·
David tweet media
ZXX
0
0
2
41
David
David@dd_tch·
top 15% of cursor users. I know that @AlexReibman should be definitely in top 10 or more. What about our Agentic star @braelyn_ai ???
David tweet media
English
0
0
1
68
David
David@dd_tch·
damn, I don't feel good about it lol
David tweet media
English
0
0
0
17
David
David@dd_tch·
@braelyn_ai That’s so true. Same I previously said about android phones it’s experience ruined by google
English
0
0
1
188
Braelyn ⛓️
Braelyn ⛓️@braelyn_ai·
Antigravity is the best out-of-the-box coding agent I have used so far. I'm familiar with the alternatives. Google has done a particularly good job building it, but unfortunately they're still Google
English
7
0
19
2.7K
Braelyn ⛓️
Braelyn ⛓️@braelyn_ai·
can someone build Antigravity but without Google?
English
123
5
318
38.1K
chris
chris@chrislevan·
pitch me your company in 1 word.
English
6.6K
133
3.8K
1.2M
David
David@dd_tch·
Helpful as always
David tweet media
English
0
0
0
27
David
David@dd_tch·
1) Google veo total disaster. 2) Kling was able to do only some parts 3) Midjorney just ignores half of promts 4) Grok is the winner. I was not expect but it generated most suitable video
English
0
0
0
68
David
David@dd_tch·
last 45 minutes I was trying to generate 5 sec videos by very specific and not so much scripts with Veo, @Kling_ai, @midjourney and @grok. Here are my thoughts:
English
2
0
1
53
David がリツイート
Rohan Paul
Rohan Paul@rohanpaul_ai·
This paper builds an agentic LLM that can run the whole data science workflow by itself. It is an 8B model that plans work, reads structured files, writes and runs code, checks results, and iterates. Standard “workflow agents” break here because fixed scripts do not adapt well to long, multi step jobs. DeepAnalyze fixes that with 5 actions, Analyze, Understand, Code, Execute, and Answer, so the model can switch between thinking and doing. Training happens in 2 stages, first single skills are strengthened, then multi skill reinforcement in live environments. They also synthesize step by step trajectories so the model sees full examples of planning, coding, and using feedback. Rewards are hybrid, simple checks like correctness and format plus an LLM judge that scores report usefulness and clarity. The result is autonomous orchestration, choosing the next best action, and adaptive optimization, improving decisions from environment feedback. Across many benchmarks, this 8B model beats most workflow agents and can produce analyst grade research from raw structured data. --- Paper – arxiv. org/abs/2510.16872 Paper Title: "DeepAnalyze: Agentic Large Language Models for Autonomous Data Science"
Rohan Paul tweet media
English
13
84
466
66.3K
David
David@dd_tch·
Comet, Atlas, Chrome… we need @grok in this game. Or should I say new era of browser wars?
English
2
0
2
39
David
David@dd_tch·
@braelyn_ai Haha to fix a hook we need a hook that hook you up… few moment later half or react developers are hookers 😄 pardon my pun
English
0
0
3
985
Braelyn ⛓️
Braelyn ⛓️@braelyn_ai·
c'mon bro just one more hook bro. just one more hook and we'll fix it all bro.
Braelyn ⛓️ tweet media
English
146
200
4.1K
206.8K