Coding, Cloud Technologies, Software Development, AI Agents
Joined July 2010
- Tweets 1,144
- Following 113
- Followers 130
- Likes 565
82 Photos and videos
Pinned Tweet
Mar 12
I just open sourced SnapDrift: visual regression checks for apps in GitHub Actions.
1
1
1
366
codesamplez retweeted
Jun 13
4 awesome open-source AI projects:
๐ธ /last30days (new search engine)
๐ธ agent-skills (full dev skills)
๐ธ open-notebook (local notebook lm)
๐ธ headroom (save 90% on AI bills)
29
59
780
84,885
Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere.
GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans.
docs.z.ai/devpack/latest-modโฆ
As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks.
API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License.
The future of AI is open, and it belongs to the people.
345
979
8,172
2,283,333
AMD Ryzen AI Halo. The ultimate local AI developer platform.
Pre-order now: bit.ly/4xv5PJS
โก Up to 128GB unified memory
โก Support for models up to 200B parameters
โก Windows & Linux support
โก Ready-to-run AI workflows out of the box
Build, prototype, and deploy locally without cloud constraints.
217
296
2,892
426,063
codesamplez retweeted
Jun 12
Nearly frontier open source coding model. Congrats to the Kimi team.
I would love to see this tested against DeepSWE
Jun 12
๐ Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!
๐ท Improved coding & agent performance over K2.6: 21.8% on Kimi Code Bench v2, 11.0% on Program Bench, and 31.5% on MLS Bench Lite.
๐ท Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
๐ท Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.
โก๏ธ 6x High-Speed Mode coming soon!
๐ Available today via Kimi API and Kimi Code.
๐ Kimi Code: kimi.com/code
๐ API: platform.moonshot.ai
34
35
831
61,406
codesamplez retweeted
Jun 8
๐ฅHoly ๐ฉ! New King of the Open Source LLMs! Beats Leading OS Models. Time to start testing to verify benchmarks.
๐ Nex-N2-Pro beats
โ
Kimi-K2.6: 86% (13/14)
โ
MiniMax: 100% (8/8)
โ
GLM-5.1: 100% (13/13)
โ
DeepSeek-V4-Pro: 92% (11/12)
ยป Opus 4.7: 45% (5/11)
ยป GPT-5.5: 30% (3/10)
Jun 4
๐ข Nex-N2 is here!
A family of agentic models that doesn't just think, it acts!
Coding, search, tool use. All fused into a single agentic reasoning loop.
- Adaptive Thinking, auto-scales reasoning depth per step. Saves ~20% tokens, zero performance loss.
- Coherent Thinking, one thinking paradigm across search, coding, and tool use. No more fragile mode-switching.
๐ Result: Tier-1 open-source performance on SWE-bench, Terminal-Bench, GDPval, and more, tracking GPT-5.5 and Opus 4.7.
๐ Open-weight. Try it now.
๐ nex-agi.com/
๐ฆ huggingface.co/nex-agi/Nex-Nโฆ
modelscope.cn/models/nex-agiโฆ
github.com/nex-agi/Nex-N2
45
104
1,404
221,587
codesamplez retweeted
Jun 1
Several sleepless nights later, M3 is finally here.
Coding frontier. 1M context. Native multimodal input.
The first open-weights model to bring all three together.
Hope you all like it ๐
p.s. M3 has already submitted a lot of PRs into MiniMax Code.
Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities
- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero
API: platform.minimax.io
Token Plan: platform.minimax.io/subscribโฆ
๐New! MiniMax Code: code.minimax.io
Weights & Tech Report in ~10 Days
77
57
1,322
68,023
codesamplez retweeted
May 31
thePMIsNotGonnaLikeThis
8
5
136
6,947
codesamplez retweeted
May 21
20
103
679
267,207
codesamplez retweeted
๐๐คฃ๐, ๐ถ
47
980
7,739
216,452
codesamplez retweeted
May 22
Mfs clicking "accept all" on 31,589 Claude Code changes without reading a single line of code be like
6
16
114
7,193
codesamplez retweeted
May 19
oMLX 0.3.9rc1 released.
Highlights:
- Low-memory Macs stay stable instead of getting killed by the OS
- DFlash bumped to v0.1.7 (thanks to @bstnxbt's dflash-mlx). Qwen thinking/GDN fix, Etc.
- Chunked prefill. A long prompt no longer blocks decode for everyone else
- Multi-tasking in the admin chat. Run multiple chats in parallel
- Real-time memory bar in the admin dashboard
- Hermes Agent quick launch, "omlx launch hermes"
Plus a lot of bug fixes and new contributors in this cycle. Thanks everyone!
github.com/jundot/omlx/releaโฆ
10
13
121
8,271
codesamplez retweeted
May 19
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
7,989
11,147
150,230
27,572,412
codesamplez retweeted
May 17
Minor in Computer Science.
Major in Claude Code.
113
1,268
24,561
413,873
