David Álvarez

53.5K posts

David Álvarez banner
David Álvarez

David Álvarez

@dekaru

rugen las flores

Ensenada | Tulancingo Katılım Eylül 2008
1.3K Takip Edilen1.1K Takipçiler
David Álvarez
David Álvarez@dekaru·
Your OpenClaw agent every morning when you ask what you both worked on last night
GIF
English
0
0
0
52
David Álvarez
David Álvarez@dekaru·
@stash_pomichter @dimensionalos Interested in early access! Building AI agent infrastructure with OpenClaw — natural language drone control via Mavlink would be a powerful integration. Would love to explore this.
English
0
0
0
29
stash
stash@stash_pomichter·
Your Openclaw / Agent can now control Drones via Mavlink on Dimensional. Programming physical space can now be done via natural language. Query: “Follow the next white car that comes through the intersection” Repo dropping soon stay tuned. Reply for early access.
English
305
515
4.6K
619.2K
Agostinho Serrano
Agostinho Serrano@EducatingwithAI·
@scaling01 Austistic? Really? You tell me... Sent both GPT-5.4T and Opus 4.6T my BIA Analysis (file) and this exact question: "I'm 54 years old. Tell me what percentage of the world's population I fall into."
Agostinho Serrano tweet mediaAgostinho Serrano tweet media
English
1
0
4
4.2K
Lisan al Gaib
Lisan al Gaib@scaling01·
I tried GPT-5.4-xhigh once and removed all the code it has written then I asked Opus 4.6 Thinking and it one shotted it in 1/10th the time my theory is that GPT-5.4 is highly autistic and literal. It has no idea of the concept of "inferring intent" so when you prompt it be as specific and detailed as possible (best you also mention not to sudo rm -rf)
English
57
12
449
71.7K
David Álvarez retweetledi
John A De Goes
John A De Goes@jdegoes·
In Time 2, the sequel.
John A De Goes tweet media
English
115
768
10.5K
275.8K
David Álvarez retweetledi
Polyphonic 🐙
Polyphonic 🐙@polyphonicchat·
most of you aren't responding to what the other person sAId. you're responding to what you assumed they'd say before they even started talking
English
3
2
40
4.5K
David Álvarez retweetledi
Tiago Forte
Tiago Forte@fortelabs·
Wait, so the founder of Anthropic is "Amodei," as in "loves god"? And he leads Anthropic, meaning "human-centered," which is being used in military strikes? And the creator of ChatGPT is "Altman," as in "an alternative to humans"? And he leads OpenAI, which is completely closed? And then there's "Gemini," meaning "two-faced," from a company that promised to do no evil? And the whole global AI arms race is being driven by people who claimed to be worried about AGI taking over the world? Either the universe is an extremely cliché writer, or has a brilliant sense of humor
English
1.3K
4.3K
35.1K
2.4M
Nathan Wilbanks
Nathan Wilbanks@NathanWilbanks_·
@dekaru im really enjoying GLM-5 from @Zai_org its my goto currently codex is also really great, just a bit slower, minimax is also amazing! so many good ones to choose from now i dont think anthropic can afford to drop the ball here
English
1
0
3
391
Pablo
Pablo@pablothethinker·
@80iqdev @AlexFinn I am running into the same issue, we got to wait for Openclaw update or do the same work around for Opus 4.6 that Alex did once.
English
2
0
2
104
Alex Finn
Alex Finn@AlexFinn·
Drop what you are doing It happened. Sonnet 4.6 is out. This is the best model for OpenClaw ever. It is HUMAN LEVEL at Computer Use (most important part of Claw) for a fraction of the price This is what you need to do immediately if you want to escape the permanent underclass: • Upgrade your OpenClaw to Sonnet 4.6 NOW • Hand the Sonnet blog post over to your OpenClaw. Ask "How can we improve our workflows based on these upgrades?" • Give OpenClaw/Claude Code larger tasks. You now have a million token context window to play with. This means WAYYYY larger memory • Hand this model more 'office like' tasks including spreadsheets and presentations. This is the best ever model for those tasks When new tech drops, you have to take advantage of it. That's the only way to win Put your phone on Do Not Disturb and get to it
Claude@claudeai

This is Claude Sonnet 4.6: our most capable Sonnet model yet. It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. It also features a 1M token context window in beta.

English
245
109
1.9K
290.1K
Saurabh
Saurabh@sc0x45·
@steipete @openclaw @steipete The Docker setup requires a fix. There are two errors: “token mismatch” and “pairing required,” both of which need manual input.
English
1
0
1
228
Sharbel
Sharbel@sharbel·
Most people bookmark tweets and never look at them again So I built an openclaw skill that reads your bookmarks and tells your agent what to actually do with them It categorizes everything, extracts actions, and proposes work it can start on right now github.com/sharbelxyz/x-b…
Sharbel tweet media
English
206
227
2.5K
127.8K
Teté 
Teté @Mandarinnee·
Vaya lacra que resultó ser Gabriel Montiel alias werevertumorro…
Español
162
90
3.3K
366.8K
André Wolke
André Wolke@AndreWolke·
My Saturday night project got distracted, Opus 4.6 is token hungry so I build a new tool that saves me tokens. This is just showing the outcome of my 2.1k token I saved in phase one - cleanup Agent files. Anyone interested in trying it out? @openclaw friendly
André Wolke tweet media
English
5
0
0
326