@EvaSpannagl I’ll be in SF from OKC next week. I would love to go! I lead our local AI community meet ups in Okc.
English
Josh Birdwell
3.6K posts
Josh Birdwell
@joshdbirdwell
Senior Staff Engineer at @YouVersion, @Cursor_ai Ambassador, Organizer of Oklahoma AI User Group. Always tinkering with AI, Husband to @madisonbirdwell
Oklahoma City, Oklahoma Katılım Kasım 2009
2.5K Takip Edilen852 Takipçiler
gpt 5.5 party in our SF HQ on 5/5, if you're not located in SF we pay for your flights and hotel
application closes today 5.55pm
luma.com/5.5
English
English
Code w/ Claude starts next week in SF and the livestream is open to anyone.
Sessions include what's new in Claude Code + the Platform and how @github, @cursor_ai, @Replit, @cognition, @harvey and more are building with Claude.
Claude@claudeai
Our developer conference Code with Claude returns this spring, this time in San Francisco, London, and Tokyo. Join us for a full day of workshops, demos, and 1:1 office hours with teams behind Claude. Register to watch from anywhere or apply to attend: claude.com/code-with-clau…
English
I joined @cursor_ai ambassador program today. I’m pumped to bring more events to Oklahoma. Excited to share more soon.
cursor.com/ambassadors
English
was super fun building this feature, lmk what you think!
Cursor@cursor_ai
Cursor can now attach demos and screenshots of its work to PRs it opens. Your team can review artifacts created by cloud agents directly in GitHub.
English
@KevinDuganJr What do you mean? I maintain madden exporter. I can update it to handle stats.
English
@joshdbirdwell Do you think the individual(s) maintaining Madden Exporter will modify the tool to include Stats? Someone using my site is asking about it.
English
The Madden Exporter has taken some nice changes since I last seen it! @joshdbirdwell
Are you going to add stats to the available download anytime soon?
English
@KevinDuganJr Boo. After they stopped doing the companion app it’d been way harder.
English
@joshdbirdwell Looks like only "schedule" is being exported from the /week portion, no stats are exported.
English
@petergyang @garrytan @OpenAI @openclaw It also will say the best next action is x and then not do it. Or I’ll say let’s build this. It will then explain and stop short of building it.
English
Codex team and @OpenAI have a huge opportunity right now to:
1. Tell @openclaw users how to switch to gpt subscription (I think it’s just telling the bot to switch the model?)
2. Fix GPT’s personality (maybe even sharing a prompt will help in the short term?). This is the main reason why ppl prefer using OpenClaw with Opus.
English
Can’t wait to join the team at @openai building codex. Would love to hear what you love about it or want changed. We’re moving fast. DMs open.
English
@_catwu Getting Claude code to run on long running tasks, utilizing scheduled tasks and loops in interesting use cases, how to setup remote env well for Claude code cloud agents.
English
Excited to see everyone at Code with Claude! What would you like to hear from us at this year's sessions?
Claude@claudeai
Our developer conference Code with Claude returns this spring, this time in San Francisco, London, and Tokyo. Join us for a full day of workshops, demos, and 1:1 office hours with teams behind Claude. Register to watch from anywhere or apply to attend: claude.com/code-with-clau…
English
@amorriscode @tannerlinsley This is excited. I was about to use cmux but sounds like this will be the next evolution.
English
@tannerlinsley let me know if you want in on the beta for the new CC Desktop UI/UX
English
Ghostty was fun, but time for something else.
I still love opencode, too but with CC plans dead on it… I’m feeling lost.
Full GUI?
T3 Code?
Opencode GUI?
Warp?
Back to cursor?
Try CC again?
Raw Codex?
My 🧠 hurts and I just need to keep shipping.
English
Excellent watch.
sarah guo@saranormous
Caught up with @karpathy for a new @NoPriorsPod: on the phase shift in engineering, AI psychosis, claws, AutoResearch, the opportunity for a SETI-at-Home like movement in AI, the model landscape, and second order effects 02:55 - What Capability Limits Remain? 06:15 - What Mastery of Coding Agents Looks Like 11:16 - Second Order Effects of Coding Agents 15:51 - Why AutoResearch 22:45 - Relevant Skills in the AI Era 28:25 - Model Speciation 32:30 - Collaboration Surfaces for Humans and AI 37:28 - Analysis of Jobs Market Data 48:25 - Open vs. Closed Source Models 53:51 - Autonomous Robotics and Atoms 1:00:59 - MicroGPT and Agentic Education 1:05:40 - End Thoughts
English
@haider1 Will they release a better harness soon after recent hires?
English
xAI has caught up so fast to openai and google
they started years later, and it's actually very impressive that they're already close to openai and google despite the late start
and not to forget:
grok 5 is 7 trillion parameters and is trained on a blackwell-powered colossus cluster
English
@joshdbirdwell @theo Fixing tests for an hour, you say? (Funny to me, considering my recent tweets, hahaha)
🫶
English
Just let Opus go for over an hour on a new feature. When it was done, I asked how I can test it.
20 minutes later, it realized I can't test it because it did the whole thing entirely wrong.
Idk how you guys use this model every day for real work 🙃
English
@tommygeorge @theo I was able to do that when it’s fixing tests after an upgrade to a core library.
English
@theo We definitely don’t let it “run for an hour” on my side of the glass. 😅😬
I don’t know how anyone gets that kind of thing to work.
English