Blizzy

633 posts

Blizzy banner
Blizzy

Blizzy

@blizzy888

For dust you are, and to dust you shall return

Katılım Ağustos 2016
424 Takip Edilen180 Takipçiler
Tibo
Tibo@thsottiaux·
You can now keep codex going for days. With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.
Felipe Coury 🦀@fcoury

/goal also lands in Codex CLI 0.128.0. Our take on the Ralph loop: keep a goal alive across turns. Don't stop until it's achieved. Built by my co-worker and OpenAI mentor Eric Traut, aka the Pyright guy. One of the GOATs I get to work with daily.

English
335
255
5.4K
685.6K
Blizzy
Blizzy@blizzy888·
@sama Sam uses windows?
English
0
0
0
16
Sam Altman
Sam Altman@sama·
wow y'all love 5.5 we should think of something nice to do to celebrate!
English
2.6K
290
11.2K
772.5K
Arena.ai
Arena.ai@arena·
GPT-5.5 by @OpenAI is now live in the Arena, landing across multiple leaderboards. Here’s how it ranks by modality: - Code Arena (agentic web dev): #9, a strong +50pt jump over GPT-5.4 - Document Arena (analysis & long-content reasoning): #6, on par with Sonnet 4.6 - Text Arena: #7, Math #3, Instruction Following: #8 - Expert Arena: #5 - Search Arena: #2 - Vision Arena: #5 Strong, well-rounded performance, especially in Code (+50 pts vs GPT-5.4). Congrats to @OpenAI on the release. Full category breakdowns by modality in the thread.
Arena.ai tweet media
OpenAI@OpenAI

Introducing GPT-5.5 A new class of intelligence for real work and powering agents, built to understand complex goals, use tools, check its work, and carry more tasks through to completion. It marks a new way of getting computer work done. Now available in ChatGPT and Codex.

English
347
132
1.9K
1.4M
Blizzy
Blizzy@blizzy888·
@theo Not for long
English
0
0
2
30
Theo - t3.gg
Theo - t3.gg@theo·
For the first time ever, all three major labs are tied on Artificial Analysis
Theo - t3.gg tweet media
English
145
108
3.2K
178.5K
Blizzy
Blizzy@blizzy888·
No GitHub on attach codebase seems like a major oversight for @claudeai design
Blizzy tweet media
English
0
0
0
39
Blizzy
Blizzy@blizzy888·
@theo Someone got early access to 5.5
English
2
0
13
2.5K
Theo - t3.gg
Theo - t3.gg@theo·
Next week is gonna be quite the week :)
English
96
13
1.2K
105.5K
Blizzy
Blizzy@blizzy888·
I think it would be beneficial to see a score with and without agent skills as many other teams like Convex and Vercel do. One, skills can shift rankings and many teams have adopted skills; Two, would be interesting to see what skills actually make a difference(expo skills, your skill, Vercel react native best practices), and how much of a difference they make
English
0
0
0
198
Callstack Engineers
Callstack Engineers@callstackio·
Fresh React Native Evals run is live. Two highlights from today's snapshot: - new categories: Lists and React Native APIs - Claude Opus 4.7 currently scored below Claude Opus 4.6 Learn more 🧵
Callstack Engineers tweet media
English
4
8
75
41.1K
Mikeysee
Mikeysee@mikeysee·
as you might expect, Opus 4.7 is good at @convex
Mikeysee tweet mediaMikeysee tweet media
English
7
1
31
5.6K
Blizzy
Blizzy@blizzy888·
@theo New clanker is just as stupid and retarded.
English
0
0
0
87
Theo - t3.gg
Theo - t3.gg@theo·
How are people feeling about opus 4.7 so far?
English
791
14
1.7K
386.5K
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
883
1.5K
14.7K
3.3M
Tibo
Tibo@thsottiaux·
Codex just got a lot more powerful. Computer use, in-app browser, image generation and editing, 90+ new plugins to connect to everything, multi-terminal, SSH into devboxes, thread automations, rich document editing. Learns from experience and proactively suggestions work. And a ton more.
Tibo tweet media
English
425
373
5.2K
436.9K
David Ondrej
David Ondrej@DavidOndrej1·
> open Hermes Agent > switch to Opus 4.6 Fast > restart gateway your agent just got a lot more powerful
David Ondrej tweet media
English
27
3
106
20.8K
Dan Robinson
Dan Robinson@danrobinson·
Is there a better solution to Codex laziness than this?
Dan Robinson tweet media
English
106
3
254
42K
Magnus Müller
Magnus Müller@mamagnus00·
Codex is horrible for auto-research. If you try to say "run in a loop the entire night", it just stops after a few turns. The simplest hack: - Explain one step of your loop and just queue hundreds of them.
Magnus Müller tweet media
English
27
8
252
35.3K
Blizzy
Blizzy@blizzy888·
@theo made the video one day too early lmfao
English
0
0
0
14
Theo - t3.gg
Theo - t3.gg@theo·
We need to talk about the Claude Code rate limits
English
128
58
1.1K
105.8K
Blizzy retweetledi
Tre B
Tre B@trerbbb·
Anthropic deserves to be a supply chain risk after this. This is absurd, first the rate limits, now this!? This company is literally public enemy number 1. @realDonaldTrump please erase this company, they are filled with greed and should no longer exist. On Good Friday too, what a satanic organization. #claude #openclaw #ai
Tre B tweet media
English
0
2
6
161