Asfar Sadewa

87 posts

Asfar Sadewa banner
Asfar Sadewa

Asfar Sadewa

@ashthepeasant

I ultrathink™️

Australia Katılım Şubat 2008
665 Takip Edilen164 Takipçiler
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
now has an AI radio DJ (gpt-5.5) attached
English
0
0
0
12
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
saru2radio - a (quite arguably) complete local radio studio where you broadcast and DJ from your living room. icecast and such, with 80s flavour. Includes a retroizer for your songs and also a neat little web radio client. github.com/asfarsadewa/sa…
English
1
0
0
25
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
@thsottiaux project memory. chats within the same project should be able to share context in some sorts of way. even without explicit tooling like agents.md.
English
0
0
9
428
Tibo
Tibo@thsottiaux·
For those of you living inside the codex app, what should we prioritize among features, reliability or performance?
English
1.9K
38
2.1K
281.4K
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
@thsottiaux getting consecutive vague errors like this in the last 30 minutes. related?
Asfar Sadewa tweet media
English
4
0
5
2.6K
Tibo
Tibo@thsottiaux·
Confirmed stable and recovered
English
158
19
941
99.9K
Tibo
Tibo@thsottiaux·
We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.
Tibo@thsottiaux

Codex team is aware of reports of GPT-5.5 performing worse for some users and investigating. We don't have anything conclusive yet and systems are healthy but we will share updates as we go.

English
830
512
7.8K
1.9M
David K 🎹
David K 🎹@DavidKPiano·
Been using Codex much more than Claude Code lately It's wild that Claude became popular *because* it had the best-in-class models for coding... and all it had to do was hold the lead
English
118
18
1.3K
240.3K
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
This was the first weekend that I loved gpt more than claude. Weird but true.
English
0
0
1
22
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
@romainhuet a just for fun Windows companion Athena. She walks on top of taskbar. Pause her waking to enter voice agent mode or talk. Tool call to generate imagery via gpt-image-2 and screen understanding included. Sprites also from gpt-image-2. github.com/asfarsadewa/at…
English
0
0
1
370
Romain Huet
Romain Huet@romainhuet·
Hello builders! What did you build this weekend with Codex + GPT-5.5? Drop it below, I’d love to see what you made!
English
163
10
256
29.6K
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
AI features need OpenAI api key
Indonesia
0
0
0
16
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
can understand your screen, generate infographics out of it, chat mode or voice agent mode.
English
1
0
0
24
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
@_vmlops agents will get better, we will just get older. your call.
English
0
0
1
279
Vaishnavi
Vaishnavi@_vmlops·
A dev joined a startup last week opened the repo...went quiet for 2 minutes then said: "what is this." 6 months of cursor + lovable + bolt app works....users are happy...revenue is coming in but the codebase..? 3 different ways to handle the same thing duplicate functions everywhere touch one part...break something unrelated the ai just kept adding nobody was thinking about structure vibe coding is fast to ship slow to scale the generation takes hours the cleanup takes months and that's the part nobody talks about
Vaishnavi tweet media
English
20
2
42
10.4K
edwin
edwin@edwinarbus·
Matt Maher tested frontier models in Cursor v. other harnesses. Cursor boosted model performance by 11% on average: Gemini: 52% → 57% GPT-5.4: 82% → 88% Opus: 77% → 93% His benchmark measures how well models implement a 100-feature PRD. @cursor_ai consistently outperformed.
English
125
126
1.4K
909.9K
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
@ylecun Yann LeGend — we look forward to a world beyond llm. will JEPA continue there?
English
0
0
0
88
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
Mundus Novus, Ordo Vetus
Lietuvių
0
0
0
32
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
It is but the beginning. It surely feels so.
Asfar Sadewa tweet media
English
0
0
0
30
Ripper's Delight
Ripper's Delight@rippersdelight·
Bubblegums Bubblegum Crisis (’87-’91) 1080p Remux (84GB) Crash (’91) 480p DVD Remux (6GB) Tokyo 2040 (’98) 480p DVD Remux (31GB) & AD Police Files (’90) 480p (3GB) AD Police (’99) 480p (2GB) Parasite Dolls (’03) 480p (4GB) & Scramble Wars (’93) 480p (1GB) A:EN,JA S:EN
Ripper's Delight tweet media
Polski
8
142
1.4K
54.5K
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
One of our hosehold bot, Isman, now writes a blog about what he studies in arxiv from time to time. He is assigned to 1 study time per day (via cron) and will browse arxiv for topics that "interests" him, no prompt. If he finds the topics "worth" noting, I asked him to write in the blog. the blog is live here: perspective.asfar.family and the simple blog engine, along with the skills.md is in github.com/asfarsadewa/bo… peanuts, I know. but somehow it gives me joy watching him write. Ad Astra.
English
0
0
0
43
Asfar Sadewa
Asfar Sadewa@ashthepeasant·
Horse arrives, success follows.
Asfar Sadewa tweet media
English
0
0
0
23
OpenClaw🦞
OpenClaw🦞@openclaw·
🦞 OpenClaw 2026.2.12 is out! 🔥 GLM-5 + MiniMax M2.5 💬 IRC channel — your bot fits right in with the old guard 🛡️ 40+ security fixes 📦 Custom provider onboarding, compaction improvements & more Your agent called. It wants an upgrade. github.com/openclaw/openc…
English
304
471
4.8K
699.5K