Ilpo Leppänen retweeted
For the first time in the history of AI models, a model has survived an entire month without losing its crown.
Opus 5.5 needs to be studied.
Ilpo Leppänen retweeted
most teams have a spare mac doing nothing. it can now run 400+ sandboxes
Ilpo Leppänen retweeted
Do you use git to version control CAD STEP files?
I've added a diff to my STEP tool. Automatic PR comments showing what has changed graphically and in real engineering terms
github.com/pzfreo/step-diff-…
The picture is useful but the feature analysis is the core value (see below)
Ilpo Leppänen retweeted
Tibo just dropped a MASSIVE hint about where OpenAI is taking its models next.
One of the biggest complaints about OpenAI models is that they follow instructions without truly understanding what the user is trying to accomplish.
Now Tibo is explicitly highlighting Terra's improved ability to understand nuanced requests.
Just last week, The Information reported that Anthropic was developing a model capable of inferring users' underlying intentions and even anticipating goals they haven't explicitly stated.
Both companies appear to be converging on the same frontier where models understand what you actually want, not just what you tell them to do.
Ilpo Leppänen retweeted
T3 Code version 0.1.3 is now live! Stable is fully caught up to the nightly :)
Pretty small release, here's what's changed since v0.1.2:
- Complete redesign of the app to look significantly better
- Share threads with a guest in 2 clicks
- Opening a thread loads 85% less data, and cold connects send up to 93% less.
- Cmd+K search is comically better.
- T3 Connect promotes to LAN for using other boxes on same network
- File preview overhaul, now supporting office files, mermaid diagrams, sqlite dbs, audio files, pdf annotations, svg attachments, and more
- T3's agent instructions are 60% shorter, and the MCP tool schemas are a third smaller.
- "steer" is default (queueing sucks)
- More reliable PR linking
- You can now add custom instructions for title gens
- Muse Code now shows in usage tab
- All emdashes removed forever
- Various accessibility wins for screen reader support
- Code highlighting got way faster with @.pierre/highlights
- PR timeline, code tab, summary and search got way faster
- Streaming text updates are batched, so long runs use less CPU
- ~480 other things got merged that I forgot lol
...okay maybe it's a big release.
💦 dream
My dream AI agent tool:
- Opus 5.5 Level Model (never delegates to worse)
- Spins up cloud and local code sessions
- Dots level real time voice / tool use
- Codex level Computer use on local sessions
- Claude Artifacts quality decks, docs and design
- Mobile app is UI of duet
- Inline mini apps (What Grokbot is doing with email and slack, but do this with alot more tools)
- Webhooks (Like Grokbot has)
- Built in social media access across all platforms
- Plugins (of course)
In summary:
I want an always on, frontier model powered employee that can use its own computer, and can use my computer 24/7 that self organizes all of its tasks into channels so that its easy to keep track of all the things we've done together. And I want to be able to control this agent on mobile, web, desktop, and most importantly real time voice.
Ilpo Leppänen retweeted
Just noticed my skills repo is at 50,000 stars and 2,7 million downloads, thanks!
More skills coming soon, you’ll like them.
github.com/emilkowalski/skil…
Ilpo Leppänen retweeted
🎉 Introducing OpenDuet
Self-hostable, proactive AI agents that you own and works with ANY agent harness.
Includes:
- Build, generate, and edit live assets
- Human-in-the-loop approvals
- Computer use
- Mobile, Web, and Channels
Repo → github.com/CopilotKit/OpenDu…
Powered by @CopilotKit and AG-UI.
Clone this template and customize it however you want. Enterprise-ready.
Ilpo Leppänen retweeted
This man left Anthropic to play WoW Forever.
Fking legend.
I’ve left Anthropic after more than a year of working on Claude Code and seeing it scale larger than I ever imagined.
I have really loved working at Ant and believe deeply in the mission, and most of all, the idea of a race to the top.
The idea that if we work hard and responsibly, we can raise the bar and inspire others to great outcomes. And if we all push each other to be better, things can be radically good. I will carry the spirit of this with me forever.
My colleagues at Anthropic are the most talented, thoughtful, competent, and earnest people I have ever met. I am glad they are at the wheel and trust them deeply.
To the community on X, thank you for everything. You’ve made this the most fun (and sometimes stressful) job I’ve ever had.
For me, it is time for a bit of a break before diving into something new.
If you want more excellent Claude Code content, you should follow @addyosmani , @lydiahallie, @_catwu, @ClaudeDevs and of course @bcherny who started it all.
Ilpo Leppänen retweeted
New: domain-driven design for Effect, in alchemy.run/domain.
Translate business requirements directly into working software and integrate into your alchemy infrastructure.
Ilpo Leppänen retweeted
[email protected] is out.
The alchemy package is now split into one package per provider, cross-cloud bindings are universal, effect workflows, distilled heap/bundle optimized and much more!
alchemy.run/blog/2026-10-22-…
Ilpo Leppänen retweeted
While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected.
Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions.
Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent.
But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models?
We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem.
Read the full report: cohere.com/blog/concerning-b…
Ilpo Leppänen retweeted
GPT-6.1 Terra: delivering fast and capable computer use at a lower price.
GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
🤖 Made with AI
