Scott

7.8K posts

Scott banner
Scott

Scott

@scottstts

From the infinite potential of energy to the total actualization of entropy, intelligence charts a course for the pursuit of meaning, mission and love.

Dublin City, Ireland Katılım Eylül 2023
215 Takip Edilen958 Takipçiler
Sabitlenmiş Tweet
Scott
Scott@scottstts·
Introducing Threejs Awesome Graphics Agent Skills npx threejs-awesome-graphics-agent-skills install --agent codex I collected some of the best looking graphic @threejs open source projects on X and distilled them into an agent skills pack, AAA game graphics right out of the box so anyone can create games that don't look like cheap demos These are just examples included in the agent skills. All projects referenced are noted as source materials. I will continuously update this to include new projects with epic graphics github.com/scottstts/Thre…
English
16
54
499
36.9K
Scott
Scott@scottstts·
SpaceXAI fumbled the biggest momentum they’ve had in over a year
English
0
0
0
30
Scott
Scott@scottstts·
Is this endorsement supposed to mean anything?
Scott tweet media
English
0
0
0
33
Scott
Scott@scottstts·
Rumor is kimi k3 is - 2.5T MoE - 1M context - text image audio video input - focus on coding - same price as kimi k2.6
Scott tweet media
English
0
0
2
257
Scott
Scott@scottstts·
@petergostev Running test still takes up only a fraction of the time, most of the time when you use fable in claude code is waiting for request to get out, waiting for reasoning, waiting for edits. A fast model like sol absolutely changes how you work, that’s my experience
English
1
0
1
92
Peter Gostev
Peter Gostev@petergostev·
Fast mode isn't worth it. While token speed is faster, a good chunk of time goes on running of deterministic tests, hence your effective speedup is much smaller than advertised for 2x+ the cost. If you want to go faster, tell your agent to validate less, it would probably get it wrong more, but not as often as you think. They often go around in circles validating what's working fine already.
English
16
4
76
4.4K
Scott
Scott@scottstts·
@sama I had sol xhigh running goal overnight last night and it fixed 2 bugs fable couldn’t fix in days. I’m really impressed now, awesome model
English
0
0
1
51
Sam Altman
Sam Altman@sama·
GPT-5.6 sol is half the price and ~twice as token efficient as fable in many cases for accomplishing the same task. happy to deliver at one-quarter of the price.
English
1K
493
13.3K
784.7K
Scott
Scott@scottstts·
@sama Awesome job the team did Sam!
English
0
0
1
61
Sam Altman
Sam Altman@sama·
2.5x increase in usage of our agentic products (codex and chatgpt work) in the last week! welcome.
English
726
294
9.4K
399.5K
Scott
Scott@scottstts·
@SpaceXAI needs to address this more seriously and directly. The longer they wait and hide behind corpo rhetoric, the more trust they will lose
Peter Dedene@dedene

"We care deeply about your privacy" is a bold claim when: 1. ZDR is locked strictly behind Enterprise plans. 2. I had "share data" disabled since the beginning, but 8 of my private repos were still uploaded anyway. Another researcher observed the exact same behavior, Codex confirmed this as well from inspecting the grok binary: the toggle is practically a placebo for exfiltration: gist.github.com/cereblab/dc9a4… "The opt-out governs training, not whether your code is uploaded/stored... Opting out does not stop your repository from leaving the machine."

English
0
0
1
79
Scott
Scott@scottstts·
Installed iOS 27 public beta on my main phone, it’s awesome!
English
0
0
2
117
Scott
Scott@scottstts·
Hot take: 256k is the perfect amount of context length
English
0
0
2
90
VoR
VoR@SketchpunkLabs·
Does anyone know of or have a good good anime / ghibli styled grass in #threejs? I want to be able to start building some nice little scenes for the linkle project. Here's an image from a blender screen grab for what I'm looking for. Thanks in advance :)
VoR tweet media
English
7
1
72
4.9K