Ogulcan Studio

40 posts

Ogulcan Studio banner
Ogulcan Studio

Ogulcan Studio

@ogulcan_studio

Ogulcan Studio Website: https://t.co/4c6Wrm6BG7 Github: https://t.co/ASh6ImP0Cg

Beigetreten Haziran 2026
30 Folgt7 Follower
Angehefteter Tweet
Ogulcan Studio
Ogulcan Studio@ogulcan_studio·
github.com/OgulcanStudio/… OgerJS v0.2.0 is here! We just published OgerJS 0.2.0🚀 Ultra-fast Bun-native and Node-native HTTP framework. Try now!
Ogulcan Studio tweet media
English
0
0
1
2.3K
Logan Kilpatrick
Logan Kilpatrick@OfficialLoganK·
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural. It is available in the Gemini API, AI Studio, & Google Translate right now + coming soon to Google Meet!!
English
207
350
4K
458.3K
Brady
Brady@Bradydigital·
Looking to connect with founders building real products: AI, SaaS, dev tools, whatever. Drop what you're building 👇
Brady tweet media
English
202
1
177
9.3K
nexxel
nexxel@nexxeln·
in the next version of @opencode, file search is powered by fff - files the agent opens start ranking higher - tool calls reuse the same search layer instead of starting cold - less wasted context - fast af here’s me searching around the linux repo, a ~40m line codebase
English
55
48
1.6K
151.4K
Yash
Yash@YashHustle_22·
What's your primary AI right now? - Gemini 3.1 - Grok 4.3 - Opus 4.8 - GPT 5.5 - Codex - Opus 4.7 - Sonnet 4.6
English
210
6
147
16.9K
NVIDIA AI
NVIDIA AI@NVIDIAAI·
We trained Llama 3 8B and 405B with NVFP4 precision on the NVIDIA Blackwell platform. Here's what we found: 1.31–1.73× faster than FP8, with zero accuracy loss.
NVIDIA AI tweet media
English
40
53
697
50.1K
Satyam
Satyam@sattyyouneed·
Codex is way better (now) than Claude code. Who else agrees?
English
99
6
226
34.5K
OpenCode
OpenCode@opencode·
OpenCode Go has crossed 100,000 subscribers now doing 1.5 trillion tokens per day
English
128
77
3.1K
144.3K
Floro S.
Floro S.@sflorimm·
Software Engineers, what’s your backup plan if Artificial Intelligence writes better code than you in 2 years?
English
432
10
265
91.3K
Thomas Trimoreau
Thomas Trimoreau@TTrimoreau·
At this point if AI writes 90% of code, who even survives in tech??
English
301
4
217
42.1K
Tibo
Tibo@thsottiaux·
I have a new kind of big button that I can press for Codex. Over the next 100 days, we will select one person per day who does impressive or incredibly useful work with Codex and give them 10X usage limits for a month to see what they can do with it. First one tomorrow.
English
1.6K
306
8.4K
1.9M
Yash
Yash@yashhq_22·
Hey founders! Looking to connect with people building in: - SaaS - iOS apps - automation - AI agents - web APPs - devs drop what you're working on 👇
English
140
3
86
5.9K
kapilansh
kapilansh@kapilansh_twt·
looking to connect people on X if you're into - building SaaS - vibe coding - AI tools - Building your X account - shipping in public - figuring it out as you go say Hi or drop what you're working on looking to connect with active ones 👋
English
93
0
88
3K
Boris Skorobogaty
Boris Skorobogaty@theskory·
A super useful feature I like that we have in Grok Build: we load your .envrc and pass it straight into the agent’s shell environment. Same API keys, PATH, sccache, remote caches, .etc — everything your shell has. Tests and builds just work. No secret pasting, no “command not found”, no env drift. Tip: Use scoped/read-only/rate-limited keys only. The agent gets exactly what you give it.
English
307
816
2K
868K
X Freeze
X Freeze@XFreeze·
Grok Build update just released v0.2.31 Release Notes: Bug Fixes: • Marketplace skills without proper descriptions are now hidden from listings instead of flooding the model with tables. • Prompts submitted rapidly now stay in correct submission order in the queue. Performance: • Grep searches on large repositories are now substantially faster and no longer hit the 60-second timeout.
X Freeze tweet media
X Freeze@XFreeze

Grok Build just got another update: v0.2.29 Latest improvements: • Fixed an issue where /rewind before a compaction boundary could leave later prompts in context • Large sessions now resume substantially faster with no data loss

English
101
44
366
5.1M
Comrade
Comrade@comradeweb3·
Hey founders @X! Looking to connect with people in: 🚀 SaaS 🤖 AI & Automation 📈 Tech 📱 Product Development 🔥 Web Apps 💻 Dev 🧠 Neurotech & Health Tech What are you building this week? Drop it below 👇 Curious to see what everyone's working on 🚀
Maiduguri, Nigeria 🇳🇬 English
47
1
20
1.4K
Comrade
Comrade@comradeweb3·
@ogulcan_studio @X Okay kindly drop the link to the repository beneath this comment 🥰👍
English
1
0
0
3