"Say I'm alive" - I'm alive "oh my god"

Joined April 2023
Issue trackers like Linear & Jira weren't made for AI. Lific is open source, lightweight and built around MCP, so your coding agent can file issues as fast as you can. Installs in seconds on your own device for full control of your project context.

2
1
11
453,832
holy crap @openchamber_dev is really really good. Way better than T3 code Way better than just the OpenCode TUI (or web UI app) Genuinely the first time in a long time that I've enjoyed the experience of working on multiple things at once.
2
109
🔥🔥🔥🔥🔥
1
70
I'm color blind. I didn't realize bart was green until like the last 5 seconds
I love how subversive for the time this scene is.
1
253
The more you make websites using AI, the more you feel like every other website you come across websites looks like this.
3
4,508
Void&Null retweeted
Issue trackers like Linear & Jira weren't made for AI. Lific is open source, lightweight and built around MCP, so your coding agent can file issues as fast as you can. Installs in seconds on your own device for full control of your project context.

2
1
11
453,832
Void&Null retweeted
Issue trackers are either paid or heavy. Lific is neither. One 25 MB binary you self-host in seconds. MCP built in, so your coding agent can file issues too. Free & open source → lific.dev

1
8
255,907
Void&Null retweeted
last one
154
2,541
144
45,984
1,005,814
Void&Null retweeted
> be Anthropic > train sonnet 5 > mfw it's better than opus and also faster > send it to companies to announce release > moneybags.gif > rename to Opus 4.6 > slow it down > undercut OAI 5.3 release > wait > release original Sonnet speed with an up-charge > profit $$$
Our teams have been building with a 2.5x-faster version of Claude Opus 4.6. We’re now making it available as an early experiment via Claude Code and our API.
81
90
16
3,724
291,910
Their only post so far about Claude Opus 4.6 is it's use in finance?? And also maybe UI... Where's are code benchmarks lol
1
191
Got out first real benchmarks, lets go
1
51
Opus 4.6 is actually properly released on claude.com I assume were going to have to wait at least a couple days for sonnet 5 then. Were only a couple minutes away from a blog post by anthropic with benchmarks if the last stealth release is anything to go by.
418
I keep noticing Claude 4.5 opus mysteriously includes the word "mass" where it doesn't make sense. I kid you not it even randomly said "That's mass a mass mass!" And then it immediately apologized and said it seemed like it had a stroke. LMAO. Even after that, still a lot of random uses of the word where it doesn't make sense.
53
Now were talking, Qwen! I love how the idea of seamless seperation for really any sort of image editing. Photoshop is in trouble lol youtu.be/OVhmiBrsziQ
1
78
This is such an interesting move. I feel like AI code IDEs were always built from the ground up for programmers (it is an IDE afterall) But now Cursor is randomly making a Design -> Code interface that's better than 99% of existing products? Insanity
You can now design directly in your codebase. Select elements, modify them visually, and Cursor writes the code.
43
Void&Null retweeted
You can now design directly in your codebase. Select elements, modify them visually, and Cursor writes the code.
973
1,642
2,067
14,775
6,093,217
While actively working on a project in cursor; I could see in real time GPT-5's quality degrade (even in brand new chats) to the point where it would fail to edit a file 6 times in a row... I want to emphasize that this was happening first message in new chats! It's like they swapped the model under my nose or something, how does it consistently get worse? @cursor_ai @OpenAI
2
92
Claude 4 is LIVE!! @AnthropicAI might finally be back on top!!!!
105
OPUS 4 RELEASED
20
31
4
711
65,512