You might like
here’s how we spent 1T tokens at ramp 200 tokens - receipt processing 350 tokens - invoices 790 tokens - reimbursements 999,999,998,660 tokens - accidentally pushed the api key to github
thanks to modal sandboxes, everybody gets a free vm on os.rahul.gs each tab is it's own FULL VM running ubuntu dont mine crypto pls
It's true – @modal has raised a $87M Series B at a $1.1B valuation to advance the future of AI infrastructure. Thank you to @Lux_Capital, @Redpoint, @AmplifyPartners, and others. Now more than ever, AI demands a complete reinvention of traditional compute infrastructure
genweb demo from anthropic 1 year later
unlike traditional AI code generation (eg copilot, chatgpt, claude artifacts, devin), which outputs code, genweb is the LLM itself llm -> code -> app ❌ llm -> app ✅ no js, no backend code - just natural language instructions and an LLM that simulates it
our computer use agent to eliminate finance busywork, first of many to come
Introducing LLM Games 🕹️ by Ramp Labs We pit GPT-5, Grok-4, o3, Gemini-2.5, and other models against each other to play Connect Four. GPT-5 high crushed all models – winning 14/14 games. As the games progress, the models think a lot longer. View the full replays of the games…
Building slide decks automatically using AI: Alex Shevchenko from Ramp shares how they use story design and tournament selection to make great decks.
coding agents need built in leverage - let me be degen with 10x agents attempting the same task if I want to
Today, we're launching Modal Batch. Run large-scale batch jobs that scale across thousands of containers without writing a single line of YAML.
google needs to bring back their web search api asap or they'll lose agent web search forever
There was a fantastic slide in Rahul Sengottuvelu's talk on rethinking AI agents at AI Engineer Summit, and it's been stuck in my head since I first saw it. This distinction b/w "classical land" and "fuzzy land" is going to become more and more important to understand.
openai has to tell codex which codex it is to avoid confusion 😭 spotted in the codex system prompt
how about we fix our model naming by this summer and everyone gets a few more months to make fun of us (which we very much deserve) until then?
4.1 is the default model on Claude Code Proxy now github.com/1rgs/claude-co… feedback coming soon
United States Trends
- 1. Diane Keaton 148K posts
- 2. Mateer 8,725 posts
- 3. #UFCRio 14.9K posts
- 4. Oregon 55.7K posts
- 5. Annie Hall 33.8K posts
- 6. Indiana 27.3K posts
- 7. #iufb 3,669 posts
- 8. Mendoza 15.5K posts
- 9. Drew Allar 1,385 posts
- 10. Northwestern 3,966 posts
- 11. Bama 16.8K posts
- 12. Tim Banks 1,018 posts
- 13. #HookEm 3,813 posts
- 14. Sark 3,407 posts
- 15. Arkansas 10.3K posts
- 16. Oklahoma 27.4K posts
- 17. Huntington Beach 7,541 posts
- 18. Baby Boom 3,154 posts
- 19. Hawkins 3,823 posts
- 20. Raiola 1,322 posts
You might like
-
Yunyu Lin
@yunyu_l -
Lachy Groom
@lachygroom -
Harrison Chase
@hwchase17 -
Aidan Gomez
@aidangomez -
Georgi Gerganov
@ggerganov -
Humanloop
@humanloop -
Ankush Gola
@ankush_gola11 -
Lance Martin
@RLanceMartin -
Kishan Bagaria
@KishanBagaria -
Corinne Marie Riley
@CorinneMRiley -
Deepak Chhugani
@dchhugani -
Eric Glyman
@eglyman -
Enrico Shippole
@EnricoShippole -
Together AI
@togethercompute -
Jesse Michael Han
@jessemhan
Something went wrong.
Something went wrong.