Talvez você curta
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
Meet Agent Fill, our agentic form filler. Built for finance & ops teams that don't want to waste time filling out PDFs. Available today in alpha.
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 Tendências
- 1. Auburn 31.6K posts
- 2. Brewers 46.5K posts
- 3. Georgia 60.2K posts
- 4. Kirby Smart 3,987 posts
- 5. Michigan 58.3K posts
- 6. Kyle Tucker 2,572 posts
- 7. #ThisIsMyCrew 2,746 posts
- 8. Nuss 5,430 posts
- 9. Hugh Freeze 1,848 posts
- 10. Sherrone Moore 1,675 posts
- 11. Penn State 27.3K posts
- 12. #EnnisLima 3,034 posts
- 13. #UFCRio 54.9K posts
- 14. Billy Napier 2,539 posts
- 15. Indiana 48.8K posts
- 16. #MagicBrew 8,961 posts
- 17. #FightOn 1,113 posts
- 18. Andrew Vaughn 1,676 posts
- 19. James Franklin 14.5K posts
- 20. Wisconsin 19.9K posts
Talvez você curta
-
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.