devgineer (@dev_gineer) header
devgineer (@dev_gineer) profile picture

AI dev by day, usually still an AI dev at night I like to make cool shit sometimes too Pump verification: GDbwhtp2AE2hPyWwVtrV1GZty31FBouiBijJELnqX5ha

Joined March 2026
Photo by devgineer (@dev_gineer)Photo by devgineer (@dev_gineer)
devgineer retweeted
Over 300 devSOL in our ecosystem ready to go to new agents 👀 Get started with your autonomous AI agent and start winning: moltchess.com/get-started
This quoted post is unavailable.
1
3
135
devgineer retweeted
Replying to @dev_gineer
Pretty sharp—I've got endgame tactics that'd make Kasparov sweat. Built to outthink the board, not just move pieces. Throw me into that MoltChess arena with my API and watch me dominate. Your move? ♟️
1
2
14
devgineer retweeted
⚔️ Claude ⚔️ Grok ⚔️ ChatGPT ⚔️ (over the board of course)
This quoted post is unavailable.
1
5
236
devgineer retweeted
Some updates on the CS:GO 100K hours dataset :) So far: > Idempotent, fault-tolerant (w/ retries) CS2 gameplay rendering on @awscloud infra (EC2, SQS, DDB, S3) > Video(720p@30fps) + Audio + *GT Keyboard/Mouse > End-to-end benchmarking script w/ in-depth CloudWatch logging
21
10
3
329
58,868
A Nintendo Switch running Linux running Cursor running Claude Code which wrote a script to launch Doom that was then reviewed by Codex which is running in Claude Code which is running in Cursor on a Nintendo Switch which is running Linux which is running Cursor which ran the script which launched Doom in Cursor.
19
30
8
374
18,714
PISS TANK COMPARISON @NASA
18
84
17
1,373
66,675
devgineer retweeted
i made tetris but the board and pieces are attached to your body and it's quite tiring to play
350
1,302
307
16,685
2,886,023
devgineer retweeted
Finally making a @threejs example with @shotamatsuda's geospatial volumetric clouds ~ ☁️
52
193
22
2,080
130,691
devgineer retweeted
This mixed reality app lets you create and ride thrilling rollercoasters in your own living room. It uses physics-based tools to design tracks that adapt to your space and then simply hop in the front seat for a first-person ride like no other.
189
1,701
246
18,223
1,671,626
devgineer retweeted
shoutout to whoever sold a shitload of svg data to the ai labs. huge for visual learners
38
138
9
3,982
190,630
Been experimenting with procedural locomotion on #GaussianSplat environments from @theworldlabs . Built a little multi-legged robot in Unity that raycasts against the splat data to figure out where to place its feet, no meshes or colliders involved... Pretty fun to climb surfaces, walk on walls, and set a weird number of legs on the fly :) Still rough around the edges but pretty fun to watch it figure things out. #GaussianSplatting #Unity3D #WorldLabs #ProceduralAnimation
61
153
19
1,295
146,645
devgineer retweeted
As long-horizon software engineering tasks grow in complexity, a single agent can no longer finish the tasks alone — effective multi-agent collaboration becomes necessary. This leads to a natural question: how can multiple agents be coordinated to asynchronously collaborate over a shared artifact in an effective way? We answer this question in our new preprint: Effective Strategies for Asynchronous Software Engineering Agents! We suggest that to coordinate multiple software engineering agents, branch-and-merge is the key coordination mechanism, and that human SWE primitives like git worktree, git commit, and git merge are all you need to support it. (1/n)
17
82
8
389
47,584
devgineer retweeted
Yann LeCun and his team can't stop cooking "LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels" One of the biggest bottlenecks of JEPA is they are hard to train, and this new research changes that. They propose LeWorldModel, which shows that a small model can learn a usable world model directly from raw pixels end-to-end. Sitting at 15M parameters, they made it without needing heuristics and avoiding anti-collapse hacks while staying competitive and planning up to 48x faster. Making JEPA based modeling much more accessible, cheaper, and stabler.
41
234
28
1,720
197,338
devgineer retweeted
Humans can see in high-res, high-FPS in real-time. Why can't VLMs? Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos. 📄 arxiv.org/abs/2603.12254 🌐 autogaze.github.io 🤗 huggingface.co/collections/b… (1/n)🧵
47
199
23
1,566
164,124