Roscoe Rubin-Rottenberg

1.8K posts

Roscoe Rubin-Rottenberg banner
Roscoe Rubin-Rottenberg

Roscoe Rubin-Rottenberg

@knotbin

16yr old atproto dev, mysterious but largely unimportant, democratizing social @ https://t.co/b7nNzeioa1, prev. @getlsd

I'm on Bluesky more now Katılım Ekim 2021
942 Takip Edilen1.3K Takipçiler
Sabitlenmiş Tweet
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
I can't stop smiling. I just won Apple's #SwiftStudentChallenge! I've wanted to apply since I was 8. Finally eligible this year, I put so much passion into my app. I feel so lucky & excited for #WWDC2024! Thank you so much @apple ! I can't wait to keep learning as a #iOSDev!
English
24
7
206
28.2K
Ryan Dahl
Ryan Dahl@rough__sea·
unpopular opinion: “alphabet” and “meta” are great names for these tech conglomerates
English
7
2
78
7.6K
Xxi
Xxi@Xxi5olc·
@thsottiaux @knotbin It’s amazing that Tibo answers question from 16yr old vibe coder. Anthropic will just ban his account
English
1
0
3
99
Zapidroid
Zapidroid@Zapidroid·
@OpenAI "your mac" guys you live in a bubble. statistically nobody uses macs ffs. When is windows coming
English
29
0
114
8.5K
OpenAI
OpenAI@OpenAI·
Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.
English
834
1.5K
14.4K
3M
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
@BropeJim I had upgraded my CLI and still didn’t have the /memories command. I still don’t know why it’s not there, as it’s in the changelog for 0.121.0 which I have installed.
English
0
0
0
16
Walt Stevens
Walt Stevens@BropeJim·
@knotbin Can we normalize actually knowing what you're talking about before forming a strong public opinion Jesus f****** Christ
English
1
0
1
64
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
@thsottiaux Docs say /memories is in the TUI but it's not (for me at least). I'm on the latest 0.121.0 release listed in the github.
Roscoe Rubin-Rottenberg tweet media
English
1
0
0
510
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
@thsottiaux Amazing! 👏 Also I really like the new analytics tab in settings on Codex Web. Would love for that to come to the app and would also really love a contribution-graph style usage graph like Claude has.
English
0
0
1
193
Tibo
Tibo@thsottiaux·
Codex Compute efficient ✅ Always up, never down ✅ Best at hardcore engineering ✅ Crazy good app, first to escape the terminal ✅
English
443
181
5K
2.3M
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
@RyanLeeMiniMax I'm so confused. This just says personal use is allowed. It never says what's happening to commercial use. You say it's where you're "drawing a line" but then "we want commercial use to be sustainable" Are you banning all commercial use? Do they have to pay you? I have no clue.
English
0
0
0
65
Roscoe Rubin-Rottenberg retweetledi
dax
dax@thdxr·
AI safety focuses on dramatic things like bioweapons and nukes but LLMs are breaking so many systems we rely on in more boring ways via spam, noise and misinformation wish this was more of a focus
English
73
71
940
91.3K
dax
dax@thdxr·
1. this isn't true. this works exactly how codex cli does. it works exactly how every LLM api does. the newer api for making it stateful does not save any tokens 2. Copilot's billing system has changed recently and there are some slight optimizations we can make although they're minor. their system also allows us to lie about usage and extract way more requests which gets users banned. we won't do that
English
6
2
391
26.9K
Chris Banes
Chris Banes@chrisbanes·
The more I use @opencode, the more I get papercuts. - OpenAI usage uses costs you extra tokens (every request uploads the entire chat history). - Copilot uses a lot more premium requests than it should. All hidden stuff that end up costing you money.
English
29
2
172
43.9K
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
@thsottiaux I love Codex! I just unsubscribed from Claude Pro and subscribed to the new $100 Codex tier. I just really need a /undo in the CLI. My wishlist item is a GH-commit-history-style view of my past usage like Claude has.
English
0
0
0
188
Tibo
Tibo@thsottiaux·
I’m having cheesecake again and thinking about codex. But next week will be about more than cooking
English
211
46
1.9K
258.2K
Tibo
Tibo@thsottiaux·
We did it, say hi to the $100 plan! It should be the sweet spot for a ton of you. It comes with a ton of codex usage. And yes we are resetting the limits again too as I mentioned yesterday. Let’s keep building!
OpenAI@OpenAI

We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.

English
394
119
3.7K
216K
Roscoe Rubin-Rottenberg retweetledi
EFF
EFF@EFF·
After almost twenty years on the platform, EFF is logging off of X. This isn’t a decision we made lightly, but it might be overdue. 🧵(1/5)
English
877
793
4.3K
4.4M
Roscoe Rubin-Rottenberg retweetledi
Zed
Zed@zeddotdev·
Claude Sonnet’s p90 latency rose 44% in three weeks inside Zed. Today we’re launching Agent Stats: a weekly view of AI agent adoption and turn times in Zed. See the data, and what it can and can’t tell you about how people actually use agents: zed.dev/blog/agent-met…
English
10
23
410
18.2K
Roscoe Rubin-Rottenberg
Roscoe Rubin-Rottenberg@knotbin·
@Zai_org ehhh. the price increase is too much given the performance gains are minimal compared to 5.0. On Artificial Analysis, it only went up 1 point in intelligence and went down four points in coding.
English
0
0
0
267
Roscoe Rubin-Rottenberg retweetledi
Z.ai
Z.ai@Zai_org·
Introducing GLM-5.1: The Next Level of Open Source - Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo. - Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations. Blog: z.ai/blog/glm-5.1 Weights: huggingface.co/zai-org/GLM-5.1 API: docs.z.ai/guides/llm/glm… Coding Plan: z.ai/subscribe Coming to chat.z.ai in the next few days.
Z.ai tweet media
English
534
1.3K
10.8K
4.2M
OpenCode
OpenCode@opencode·
GLM-5.1 is now available in Go w/ Zero Data Retention
English
101
120
3K
194.4K
Lou
Lou@louszbd·
we open-sourced glm-5.1 agents could do about 20 steps by the end of last year. glm-5.1 can do 1,700 rn. autonomous work time may be the most important curve after scaling laws. glm-5.1 will be the first point on that curve that the open-source community can verify with their own hands. hope y'all like it^^
Z.ai@Zai_org

Introducing GLM-5.1: The Next Level of Open Source - Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo. - Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations. Blog: z.ai/blog/glm-5.1 Weights: huggingface.co/zai-org/GLM-5.1 API: docs.z.ai/guides/llm/glm… Coding Plan: z.ai/subscribe Coming to chat.z.ai in the next few days.

English
130
144
2.5K
144.5K

Keşfet

@rough__sea @Xxi5olc @thsottiaux @Zapidroid @OpenAI @BropeJim @RyanLeeMiniMax @thdxr