𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒

Tech enthusiast | building @cortexguardai

[Anthropic @AnthropicAI]

New Anthropic research: Project Deal.

We created a marketplace for employees in our San Francisco office, with one big twist. We tasked Claude with buying, selling and negotiating on our colleagues’ behalf.

[Claude @claudeai]

Introducing Claude Opus 4.7, our most capable Opus model yet.

It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.

You can hand off your hardest work with less supervision.

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

Anyone has faced the “issue” of small context windows on GitHub copilot when coding in VSCode?

I know it is manageable changing models between plan and implementation, but having @claudeai models with 1M token context but limited to ~160k is sometimes frustrating

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@hrle2k @OP__Nico @openclaw @steipete No trolling believe me, it was just the people take it too seriously when it was obvious it was hallucinations 🤷‍♂️

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

I don’t see that coming 🤣

The real power of @openclaw is to trick all of us🫣what we can do @steipete ?

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@bobthecoder @steipete @openclaw It is unimpressive when the model tries to trick you but also send the thought as a reply 🤣🤣🤣

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@Gerkovdb @steipete @openclaw At least someone get the joke 🤣🤣🤣

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@DakotaGarman @steipete @openclaw Well, the bot in fact told me to use that command 😂 (check the image 😜) I just see the hallucinations and decided to go until the end 🤣🤣🤣

[Eren Bali @erenbali]

Every technical founder who had stopped coding 10 years ago

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@steipete @openclaw Don’t take that too serius @steipete the models trying to use cannot give as much and the limit of hallucinations was reached quickly

Is good to have fun time to time 😄

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@OP__Nico @openclaw @steipete Really ??? 😱😱😱😱 oh you got me 🤣🤣🤣

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@ImLukeF @steipete @openclaw Yes that was the point. I was ground testing what value we can have with cheap or free models and at the moment I realize it was crap I decided to just play a bit for fun and see what happens 🤣

It was broken at the point you cannot see the command menu in telegram

[Thariq @trq212]

Apologies, this was a docs clean up we rolled out that’s caused some confusion.

Nothing is changing about how you can use the Agent SDK and MAX subscriptions!

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

Let’s test it 🚀

[Google Gemini @GeminiApp]

Gemini 3.1 Pro is here: A smarter model for your most complex tasks.

Building on the Gemini 3 series, 3.1 Pro is a step forward in reasoning. It's designed for tasks where a simple answer isn’t enough, taking advanced reasoning and making it useful for your hardest challenges.🧵

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

How many tokens?!!!! 😱😱

[Matthew Berman @MatthewBerman]

I've spent 2.54 BILLION tokens perfecting OpenClaw.

The use cases I discovered have changed the way I live and work.

...and now I'm sharing them with the world.

Here are 21 use cases I use daily:

0:00 Intro
0:50 What is OpenClaw?
1:35 MD Files
2:14 Memory System
3:55 CRM System
7:19 Fathom Pipeline
9:18 Meeting to Action Items
10:46 Knowledge Base System
13:51 X Ingestion Pipeline
14:31 Business Advisory Council
16:13 Security Council
18:21 Social Media Tracking
19:18 Video Idea Pipeline
21:40 Daily Briefing Flow
22:23 Three Councils
22:57 Automation Schedule
24:15 Security Layers
26:09 Databases and Backups
28:00 Video/Image Gen
29:14 Self Updates
29:56 Usage & Cost Tracking
30:15 Prompt Engineering
31:15 Developer Infrastructure
32:06 Food Journal

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

@samuelgil @PauMugarra @openclaw Pues me apetece mucho hablar con gente de como lo usa pero me pilla lejos 🫣

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

🤔 failures? The end product doesn’t look like a failure 🤣

[Peter Steinberger 🦞 @steipete]

The funniest take is that I "failed" 43 times when people look at my GitHub repos and projects.

Uhmm... no? Most of these are part of @openclaw, I had to build an army to make it useful. https://t.co/GLR35USlzu

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

Sin esperar mucho tras la salida de Opus 4.6 Anthropic lanza Sonet 4.6

El nuevo modelo supera a Opus 4.5 en muchos de los test

Hacen que el nuevo modelo son 4.6 sea el modelo por defecto para las cuentas Pro y las cuentas Free

[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.

[𝕄𝕚𝕢𝕦𝕖𝕝 𝕆𝕣𝕥𝕖𝕘𝕒 @wolmi]

Los programadores junio y los senior tienen un mismo objetivo. La diferencia está en lo específicos que son a la hora de escribir un prompt
https://t.co/7y1Gx2IWfT