synthwavedd Profile Banner
leo 🐾 Profile
leo 🐾

@synthwavedd

Followers
5K
Following
20K
Media
400
Statuses
2K

tech, ai & politics nerd

Joined August 2022
Don't wanna be here? Send us removal request.
@synthwavedd
leo 🐾
4 months
I'm excited to introduce Hieroglyph, a new benchmark for lateral reasoning. Hieroglyph measures a model's ability to identify the link between seemingly unrelated and often niche subjects. On the 20-question set of the hardest Only Connect questions, no model scores above 50%.
44
37
576
@synthwavedd
leo 🐾
3 hours
it is heartbreaking how often of an occurrence these incidents have become, and shameful that there has been such little effort to combat it may they rest in peace
@BrownUniversity
Brown University
3 hours
We are very sorry to share that we have confirmed reports of two deceased victims from the active shooting situation at the Barus & Holley engineering building. There are eight additional victims in critical, but stable condition at the hospital. There remains a shelter in place
1
0
8
@synthwavedd
leo 🐾
10 hours
In many ways Gemini 3 Flash will be a bigger deal than 3 Pro
38
7
339
@synthwavedd
leo 🐾
18 hours
GPT-5.2 xhigh in Codex would rather spend a week rewriting your kernel to fix a bug than admit it can't do it
21
2
210
@synthwavedd
leo 🐾
1 day
Time for a new one of these What's your current favourite model overall?
15
2
52
@synthwavedd
leo 🐾
1 day
Time for a new one of these What's your current favourite model overall?
15
2
52
@synthwavedd
leo 🐾
1 day
i still prefer opus 4.5 to gpt-5.2 for 95% of code tasks
22
8
413
@synthwavedd
leo 🐾
2 days
so how's everyone feeling about gpt-5.2?
43
0
86
@synthwavedd
leo 🐾
2 days
GPT-5.2 is SoTA on most benchmarks
6
5
55
@synthwavedd
leo 🐾
2 days
Claude Opus 4.5 is still SoTA on SWE-Bench Verified Total Dario supremacy
13
2
103
@synthwavedd
leo 🐾
2 days
GPT-5.2 benchmarks
4
3
47
@synthwavedd
leo 🐾
2 days
wtf holy shit LMAO
0
0
110
@synthwavedd
leo 🐾
2 days
https://t.co/LBjut1sl8O GPT-5.2 system card is out
1
5
57
@synthwavedd
leo 🐾
2 days
Interesting - native image output, new most recent knowledge cutoff in any model (Aug 31 2025), and more expensive than GPT-5 Looks like a new base
@synthwavedd
leo 🐾
2 days
https://t.co/8wpefSlcV7 It's here and more expensive than GPT-5
12
5
134
@synthwavedd
leo 🐾
2 days
GPT-5.2 introduces an 'xhigh' reasoning effort parameter
@synthwavedd
leo 🐾
2 days
https://t.co/8wpefSlcV7 It's here and more expensive than GPT-5
2
7
124
@synthwavedd
leo 🐾
2 days
https://t.co/8wpefSlcV7 It's here and more expensive than GPT-5
15
10
118
@synthwavedd
leo 🐾
2 days
Deep Research is now available on the API, powered by Gemini 3 Pro It sets a new SoTA on HLE and DeepSearchQA - impressive!
@synthwavedd
leo 🐾
2 days
Looks like Gemini Deep Research Pro is imminent 🔥
2
3
50
@synthwavedd
leo 🐾
2 days
i fear from what i've heard gpt-5.2 will not be significantly better than gemini 3 pro sama better keep that code red going 🥀
20
4
205
@synthwavedd
leo 🐾
2 days
New Codex PR seems to indicate GPT-5.2 is dropping very soon 👀 "robin" strings have been updated to "gpt-5.2" https://t.co/GuOmQb7IIp
3
6
142
@synthwavedd
leo 🐾
2 days
Looks like Gemini Deep Research Pro is imminent 🔥
7
3
206