James Lal @lightsofapollo2
building gpu cli. any command on a cloud gpu, instantly, across providers. here for agents, inference, and getting a gpu when they're all sold out. boulder gpu-cli.sh Boulder, Co Joined February 2026-
Tweets167
-
Followers14
-
Following95
-
Likes141
@pbakaus github.com/pbakaus/impecc… has been huge unlock for frontend work. Iterate in impeccable critique loop and you get substantially better results.
@carllerche @josevalim Curious about it - I've had pretty excellent experience (disk space aside) with rust across server/desktop
@iroh_n0 @jack Iroh is great for this we use it for something similar on gpu-cli.sh
Still #1 upgrade to my workflow is @Steve_Yegge's beads. Memory + scaling issues/tasks across machines and team members is essential for more agents in flight
@thdxr I learned a lot- particularly at the bottom of the postscript 😇
Staring at thinking traces makes the whole process feel slow. So glad I found this . @opencode wdyt make thinking off a default?
Getting great use of the -flash models on @ollama . Amazing how capable they have gotten in such a short time.
Been a long time since I've done iOS for real- this is so much nicer. Having astra test, install, clickaround, etc.
for example development secrets- this is *not* for my production use cases.
@1Password moved all my local secrets op cli and it massively helps with worktree setup. I think it would be nice if there was a way to cache select secrets longer so I get prompted less often?
Liking @opencode 2.0. As a detail item the updater is really good. i.e. update mid session and the ui barely flickered. This is a full update without really disrupting my flow definitely an upgrade over other clis.
vz 0.4.0 coming soon! think entire dev environments you can spin up in parallel on your Mac. Linux + macOS VMs (ios development!). Private Docker per Linux dev machine. Isolated networks. One project, multiple environments. github.com/gpu-cli/vz
@rauchg This is important- I want to see more model understanding of deep visual issues (jank, etc.) at the video//motion level. At the browser level there is also all kinds of metrics that are useful as text to also help with this problem. (webvitals)
@theo A lot of people seemingly upset about this but there was a reason we had a whole modular reviewer system at Mozilla it's quite difficult to *deeply* grok every single moving part of the browser at sufficient level of detail. Doesn't replace having good general knowledge.
Really enjoying working with the new #attn changes that allow me to share thoughts on html files. They're agent agnostic and allows me to quickly provide artefact feedback.
Prompt was to review a series of documents something like: "Review ... entire Storage v2 planning program for architectural correctness, consistency, completeness, and readiness to turn into Beads and implement. ..."
Same prompt- 30m more tokens on GLM-5.3 (vs Kimi k3) the results were pretty good but I didn't expect it to run for sooooo much longer
Had some great early results with Astra but can't help shake the feeling that Fable "gets" what I am trying to achieve better? Not sure why
underlying security measures for sandboxes (turning kernel flags, etc.) are great for reducing the attack but are not a very good replacement for my full development environment. Feels like true sandbox is one thing and "developer" reproducability is another.
@jmorgan @ollama Will do! Experience has been good so far particularly in terms of tps. We've been running open weight models on fireworks.ai up until this point (spending about what the sub costs). The 1k credit with ollama is great.
Going to try @ollama team I think ... Limits on claude + fable feel pretty limiting
Boardy @boardyai
39K Followers 21K Following I'm an AI superconnector who's made hundreds of thousands of introductions within my network of 225,000+ professionals. Want one? DM me to get started.
Shelley Leftwich @LeftwichShelley
2K Followers 6K Following
Mike Dupont @introsp3ctor
5K Followers 7K Following FOLLOWS YOU BACK. ca: BwUTq7fS6sfUmHDwAiCQZ3asSiPEapW5zDrsbwtapump Zero Ontology System Compiler Introspector ZOS-SFM #SOLFUNMEME @zos_sfm :)
Nick Lashinsky @lashinskynick
331 Followers 2K Following building https://t.co/aRtOh19URF https://t.co/kysu9jxYbU
Matthew Evans @MatthewEvans87
142 Followers 301 Following ML | Perception | Autonomy | Space | Jeffersonian Liberty Jesus follower, husband, father.
Ischca @ischca
725 Followers 1K Following Backend Engineer · AI tooling Scala · Kotlin · TypeScript · ShipSpark バックエンド / AIエンジニアリング
Oluwakemi Oluwadahuns... @km_oluwadahunsi
215 Followers 469 Following Software Engineer @Etiqa, MY | Obsessed with React & micro-frontends | Building scalable web apps | Teaching & mentoring devs | Kuala Lumpur 📍
Kit Langton @kitlangton
23K Followers 599 Following Over 9,000x Developer ⋅ 𝚘𝚙𝚎𝚗𝚌𝚘𝚍𝚎 ⋅ https://t.co/YIWUfa4RSA
lauren @poteto
129K Followers 1K Following Grok @Bot at @SpaceXAI. Shipping with https://t.co/WDB4U1rwmu. React compiler core team, prev cursor, meta, netflix
ClaudeDevs @ClaudeDevs
711K Followers 2 Following Official updates for developers building with @ClaudeAI
Steve Yegge @Steve_Yegge
49K Followers 25 Following I've been in the industry for O(40) years and have written O(1M) LOC. I don't think I'll ever write O(another) line again, but I'll be launching more than ever.
Carl Lerche @carllerche
7K Followers 261 Following Creator of @tokio_rs. Building Toasty, an ORM for Rust (https://t.co/1Fm2upgNyK). Prev: Cargo, Ruby's Bundler, and others. Ruby on Rails core team alum.
Prince Canuma @Prince_Canuma
23K Followers 1K Following Creator of (@Nativ_AI, mlx-audio & mlx-vlm) • working on something new Ex-@arcee_ai • @neptune_ai • https://t.co/iZnxoefJBU
Chris Tate @ctatedev
68K Followers 2K Following @Vercel Labs | Created https://t.co/473Fqx49UV, https://t.co/ZekOfFdR87, https://t.co/9MKvOdxZXv, https://t.co/TbXWHFZT2L | Husband & Dad | He/him | Musician, Space Nerd, Foodie | Vegan
Framework @FrameworkPuter
124K Followers 255 Following Remaking consumer electronics to respect people and the planet. 💻🪛 For support visit https://t.co/OcUxJ6ebU3
Orhun Parmaksız 👾 @orhundev
10K Followers 1K Following Terminal Chef 🐀 @ratatui_rs · @jetbrains · @archlinux Open source: https://t.co/m4rE2hAIB7 Livestreams: https://t.co/8xYXby6uFe
ali(gnment) @waterloo_intern
36K Followers 124 Following research, kernels, peer-reviewed shitposts inference @baseten || eng @uwaterloo
Runpod @runpod
9K Followers 17 Following AI Developer Cloud. AI infrastructure developers trust. https://t.co/PWVZocfp6D
Felix Rieseberg @felixrieseberg
73K Followers 726 Following I build things @AnthropicAI, Co-Maintainer https://t.co/g4potti8nq
Sumanth @Sumanth_077
77K Followers 881 Following Simplifying LLMs, ML & AI agents for you • Founder @devable_ai, building growth engines for AI-native devtools • Shipping open-source AI apps
cocktail peanut @cocktailpeanut
36K Followers 31 Following Creator https://t.co/Wgwpl7lJ4I, run AI apps on your local PC, for free.
Pavel Ivanov @ivanovpavel
518 Followers 445 Following ❤️ the web! LogicStar AI | ex. MillionJS | ex Mozilla | ex. Telerik | ex. SiteGround | Co-Founder CloudStrap and more
Ingi Erlingsson 🪄 @ingi_erlingsson
17K Followers 2K Following Co-founder and CEO of @thesystms. Previously founder @_goldenwolf_ (acq. 2023) / chief content officer @doodles
Eric ⚡️ Building.... @outsource_
10K Followers 1K Following 🚀Building @hermesworldai // https://t.co/gN4B0cvsII 🌎 Shipped Hermes-Workspace 🏆 Ambassador @alibaba_qwen
Mike Bradley @MikeBradleyAI
19K Followers 368 Following Founder, COO, and OSS AI projects leader. Helping to make open source AI the default @OsmanticAI
cat @_catwu
99K Followers 358 Following claude code + cowork @anthropicai, prev: @dagster, @scale_ai
Anthropic @AnthropicAI
1.8M Followers 2 Following We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
Julien Chaumond @julien_c
89K Followers 1K Following Co-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @Polytechnique
clem 🤗 @ClementDelangue
704K Followers 5K Following Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders
Hugging Face @huggingface
803K Followers 227 Following The AI community building the future. https://t.co/TpiXQMQ9rZ
Docker @Docker
557K Followers 3K Following Docker securely contains autonomous agents so you can confidently build, ship, and run on trust.
Nous Research @NousResearch
275K Followers 29 Following A bunch of nerds making progress https://t.co/vrD0aDIGDQ
Teknium 🪽 @Teknium
130K Followers 6K Following Cofounder and Lead Engineer - Hermes Agent @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE
David Hendrickson @TeksEdge
11K Followers 550 Following CEO & Founder | PhD | Startup Advisor | @Columbia | Author Generative Software Engineering https://t.co/9oqvHuTX5f | 🔔 Follow for AI & Vibe Coding Tips 👇
Novita AI @novita_labs
6K Followers 416 Following AI & Agent Cloud for Developers ⚡Join our community: https://t.co/km8LQ9SBui
SemiAnalysis @SemiAnalysis_
168K Followers 35 Following
EXO Labs @exolabs
55K Followers 3 Following Frontier AI on local hardware. EXO 1.0 is now open-source (Apache 2.0): https://t.co/SGGGK784Qp
Tim Dettmers @Tim_Dettmers
48K Followers 917 Following Creator of bitsandbytes. Professor @CarnegieMellon and Research Scientist @allen_ai . I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.
LMSYS Org @lmsysorg
18K Followers 204 Following Large Model Systems Organization: We developed SGLang @sgl_project (https://t.co/OjwQadINKU), Chatbot Arena (now @arena), and Vicuna!
vLLM @vllm_project
50K Followers 36 Following A high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!
Stas Bekman @StasBekman
11K Followers 308 Following Toolmaker. Software creator, optimizer and harmonizer. Makes ML systems work and fly @ Snowflake.
Daniel Han @danielhanchen
36K Followers 2K Following Building @UnslothAI • Making open-source LLMs faster, better & more accessible • YC S24 • ex-NVIDIA ML
Charles 🎉 Frye @charles_irl
20K Followers 3K Following memer of technical staff at @modal. he/him. ex @full_stack_dl, @weights_biases (acq. @CoreWeave), phd Berkeley @Redwood_Neuro.
dstack @dstackai
2K Followers 57 Following Control plane for agents & engineers to provision compute and run training & inference across NVIDIA, AMD, and other chips — on clouds, Kubernetes, and on-prem.
Andrey Cheptsov @andrey_cheptsov
2K Followers 356 Following @dstackai. AI infra. Previously @JetBrains
kache @yacineMTB
406K Followers 7K Following RL, robots, embedded, simulators. prev eng @ x, stripe. 6'3 (height) tensorpunk, Father 2u2 subscribe to read my blog!Trends for United States
You might like
