MelonLeather retweeted
Genuinely never could have imagined T3 Code getting as massive and well loved as it is today. Thank you all. Never giving up on open source 🫡
Every single time i try to go back to 6.1 sol, I come crawling back to Opus 5.5 for help...
Opus 5.5 has solved most of my issues in the past 2 weeks (even when I try to give 6.1 sol a shot at it first)
MelonLeather retweeted
Opus 5.5 is the greatest model of all time and I'm still struggling to find the ceiling.
Does anyone know if using the new Claude Subscription DirectSDK plugin for @NousResearch Hermes Agent violates Anthropic's ToS?
It lets you use your Claude Code subscription through Hermes, but I'm worried about getting my account banned
Is this officially allowed, @AnthropicAI
MelonLeather retweeted
🚨 Claude $20 vs Codex $100 Usage
After 3 weeks of tracking telemetry, one user found Claude’s cheaper plan surprisingly competitive.
Estimated monthly usage:
- Opus 5.5: ~2.5B tokens
- GPT-6 Astra: ~1.1B tokens
- GPT-6.1 Sol: ~3.2B tokens
Claude is also reportedly much faster. OpenAI has some catching up to do.
🚨OpenAI has struck a major deal with Google.
Frontier models from codex including Sol 6.1 and Astra 6 will now be available in Antigravity.
There are even rumors that a new $500 ultra subscription will be available in Gemini.
Why pay $200 for a near unlimited Claude sub when you can pay $500 to Google and OpenAI.
OpenAI is so back!
This is gonna be insanely good, mostly because of Opus 5.5
MelonLeather retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/DeepI…
1/4
I tried using GPT 6.1 SOL to do some tedious work, I ran out of tokens so fast.
I used claude code Opus 5.5 and i used it for longer, and it felt unlimited. I ended the day with 50% of my session limit left. Both $20 plans.
It also found so many mistakes that 6.1 sol made.
MelonLeather retweeted
As of now, no fly can ever know for sure if it is living in a real world or a simulated one. Must be incredibly depressing
MelonLeather retweeted
I used Orchestrator-V2 in T3 Code for a few days, and damn the team cooked hard.
It just feels all so connected, letting claude use grok from grok cli and gemini 4 argon from devin as subagents is magical in a way.
Congrats T3 Team, i really love using this feature, can't wait for new updates that make it even better (even though i honestly have no idea how could it get any better)
MelonLeather retweeted
YOUR HERMES AGENT CAN HAVE ITS OWN DESKTOP. WATCH IT WORK LIVE, TAKE CONTROL, AND HAND IT RIGHT BACK.
This is one of the standout capabilities included in Hermes v0.22.0, The Threshold Release. 🔥
It's called Bot Screen, and here's what makes it so cool:
➤ Its Own Desktop
Your Hermes bot gets a dedicated desktop on a Linux gateway, where it can use browsers, terminals, and apps without taking over your computer.
➤ Watch It Work Live
See exactly what your agent is doing on its desktop, in real time.
➤ Take Control Anytime
Need to handle a login, 2FA, or CAPTCHA? Jump in with your mouse and keyboard, complete the step, and hand control right back to Hermes.
➤ Keep Working Remotely
Your bot can continue working on the gateway even after you close Hermes Desktop or shut your laptop.
Bot Screen first landed a few weeks ago, but it's worth highlighting again as part of the new stable release.
If you missed it the first time, check out this demo! 🔥
MelonLeather retweeted
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
