Lorenzo Porras (@TheCodingSoup) header
Lorenzo Porras (@TheCodingSoup) profile picture

DevRel @Coreweave Opinions are my own.

Joined January 2025
Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)Photo by Lorenzo Porras (@TheCodingSoup)
During @reflection_ai’s private preview of Beam, I built a haunted escape room to put its coding and reasoning to the test. I created a game called “Code Your Way Out”, and it's one room with three linked puzzles. Beam has to repair a brass orrery by lining its rings up with a constellation, route the light, then program its escape through a sealed hatch. Beam never sees the room. Each turn, it gets text observations and writes Python; the code runs in a @CoreWeave Sandbox, and the game engine validates every action before the explorer robot moves. Beam was out in about 30 seconds. Super bullish on this model and really excited to see builders get this model in their hands.
1
5
2
20
3,831
Lorenzo Porras retweeted
Small models have a habit: they repeat whatever they just heard. So @TheCodingSoup built a tiny town of @liquidai LFM2.5 agents, traced every line into @CoreWeave Agent Lens, and tagged the repeats. No fine-tuning, just a harness, and the traces proved it worked: repeated lines dropped from 58% → 13%. Best part: it's all plain OpenTelemetry from Swift. No Python or TypeScript SDK needed.
1
3
1
9
896
OTEL to save the day! AI is more than python and typescript SDKs, so you should have a way to trace apps built in other languages. Checkout Agent Lens + OTEL
Small models have a habit: they repeat whatever they just heard. So @TheCodingSoup built a tiny town of @liquidai LFM2.5 agents, traced every line into @CoreWeave Agent Lens, and tagged the repeats. No fine-tuning, just a harness, and the traces proved it worked: repeated lines dropped from 58% → 13%. Best part: it's all plain OpenTelemetry from Swift. No Python or TypeScript SDK needed.
1
26
Lorenzo Porras retweeted
Today, we release d1.2 and d1.2-ultra, the state-of-the-art omnimodal decision models. d1.2 and d1.2-ultra both can process text, images, and audio with new output capabilities. > #1 on the @ArtificialAnlys Decision Index (75) > Read a value from the input (text, number or date) > Find every passage of a kind in a text (spans) > Locate things in a picture (box for one, boxes for every instance) > Estimate a number (number with a range) > Pick every option that applies (choice) 1/ 🧵
149
231
71
2,446
15,837,034
Lorenzo Porras retweeted
You can now build custom themes for Claude Code on desktop with mods! Change the colors, add an animated background, and make it your own. Just tell Claude how you want it to look, or get started quickly with the theme-examples plugin. We'd love to see what you make!
759
1,149
667
22,882
2,056,654
Lorenzo Porras retweeted
CoreWeave
2015 — You missed NVIDIA. 2016 — You missed Tesla. 2017 — You missed Bitcoin’s breakout. 2018 — You missed Amazon. 2019 — You missed Microsoft. 2020 — You missed Apple. 2021 — You missed Tesla’s second run. 2022 — You missed NVIDIA’s AI ignition. 2023 — You missed Super Micro. 2024 — You missed Broadcom. 2025 — You missed Palantir. 2026 — What are you still missing?
1
13
85
6,577
Lorenzo Porras retweeted
Congratulations to @ritazzhang on the @CloudNativeFdn 2026 Lifetime Achievement Award. Rita sits on the Kubernetes Steering Committee, co-chairs SIG Auth, and helps lead the Working Group on AI Conformance. The award goes to longtime contributors who have significantly influenced cloud native technologies, and Rita has more than earned it. We’re so proud of our 🐐
2
5
3
57
4,036
Lorenzo Porras retweeted
Thank you for this CNCF Oscar! It’s an honor. I’m grateful to be working with so many talented and caring people in this community. Shout out to @Microsoft @Azure and @CoreWeave for supporting me to do this work in this community.
Live at KubeCon + CloudNativeCon North America: Congratulations to our 2026 Lifetime Achievement Award winners, Julius Volz and Rita Zhang (@ritazzhang)! Thank you for spending over a decade building the core observability and security foundations that our community relies on every day. #KubeCon #CloudNativeCon
20
5
2
113
8,914
Lorenzo Porras retweeted
Lot’s of noise out there. Meanwhile we execute.
Today we announced our Q3 earnings: 🔹$3.7B revenue, up 168% YoY 🔹$379M adjusted operating income, well above guidance 🔹Double-digit adj. operating margins, a quarter ahead of plan 🔹1.7GW+ of active power, doubling our active footprint YTD 🔹Roughly $9B in customer prepayments and deposits in this quarter Congratulations to our team, who remain focused on executing for our customers. Read the full Q3 2026 results. crwv.co/uuHav
17
11
4
250
10,948
Lorenzo Porras retweeted
We simulated 100 CoreWeave Pirates vs 100,000 Generic Sandbox Ogres. 1,000 times. 🏴‍☠ - 5,268 CoreWeave Sandboxes - 1,196 running at once - 4,784 vCPUs + 10.5 TB RAM at peak - 40 Blackwell GPUs rendering 4K Pirates won 1,000 of 1,000 battles.
sandbox wars is a bunch of europeans in san francisco fighting each other on twitter with minecraft demos
6
2
4
24
4,695
Lorenzo Porras retweeted
Introducing CoreWeave Skills in public preview. Claude Code can build a CoreWeave Kubernetes Service (CKS) cluster, add a GPU Node Pool, serve a model with vLLM, and check that the GPUs are actually busy. Install once from CoreWeave's official GitHub repo: crwv.co/uuGEq
36
11
4
140
10,190
Lorenzo Porras retweeted
Sandbox skills coming soon!!
Introducing CoreWeave Skills in public preview. Claude Code can build a CoreWeave Kubernetes Service (CKS) cluster, add a GPU Node Pool, serve a model with vLLM, and check that the GPUs are actually busy. Install once from CoreWeave's official GitHub repo: crwv.co/uuGEq
1
2
24
1,096
Lorenzo Porras retweeted
I wanted to test Fable 5.2's quality with one-shot prompts without human feedback. Everything in this game is from scratch: models, sounds, textures. ~$550 at API pricing, ~2.7M output and 445M input tokens, heavily cached. Took 8 hours! Play it here: claude.ai/artifact/BGY1SztrA…
851
1,155
838
14,899
4,437,486
This is why Opus 5.5 stays being my #1 🤷‍♂️
Nice DeepSWE score! Does it survive a lowercase filename? Introducing MaxxBench: 89 DeepSWE tasks with small changes to the instructions or starting code. Same engineering problem, slightly different requirement. Models clustered around 74% on DeepSWE end up 23 pp apart. Good at coding, or good at DeepSWE? 🧵
47
Lorenzo Porras retweeted
check out my new article in the Anthropic eng blog. i talk about "dreaming" (offline compute) as a way to organize Claude's memory. it can correct mistakes, create memories, or build new representations. teapawt.net/AnthropicAI/status/211…
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
60
56
12
629
36,962
Lorenzo Porras retweeted
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
1,086
1,328
969
14,353
2,179,136
Lorenzo Porras retweeted
Introducing Inkling 2 Small. Scoring 31 on the AA Intelligence Index, it's a big jump over its predecessor. Inkling 2 Small is available for fine-tuning and inference on Tinker today, with full weight release planned soon. thinkingmachines.ai/news/ink…
294
585
501
6,300
1,983,190
Replying to @TheCodingSoup
@TheCodingSoup wanted to see how AI agents talk to each other when they work as a team. So he gave a swarm a shared memory and let them do their thing inside of a @CoreWeave Sandbox. They wrote 12 notes. Not one got read by another agent. (Every agent was traced in Agent Lens, so we could check.) The next run changed the timing: leads shared plans before starting, and each new agent got the relevant notes with its task. No duplicated experiments that time. Try out Agent Lens bit.ly/4z4ELRf
5
2
8
1,719
Lorenzo Porras retweeted
we know our CoreWeave sandboxes are reliable at scale because no amount of abuse attempt like we're seeing will take it down or eat up capacity $30 in free credits for you to try it today, come get sandy!
4
2
10
1,117
Swarms are everywhere, so I got curious how the agents actually talk to each other. Gave each agent its own @CoreWeave Sandbox, traced every message in Agent Lens, and added a shared memory. They wrote 12 notes. Nobody read a single one. Also really enjoying gamifying all my demos lately 🎮 More to come on this fun one.
2
2
1
6
759
Ayyy im talking to Muse non stop then 😂
Now in the Muse app: talk with your Muse in real time. And pick from multiple voices 🗣️
1
56