codesamplez

Coding, Cloud Technologies, Software Development, AI Agents

[codesamplez @codesamplez]

I just open sourced SnapDrift: visual regression checks for apps in GitHub Actions.

[David Hendrickson @TeksEdge]

🔥Holy 💩! New King of the Open Source LLMs! Beats Leading OS Models. Time to start testing to verify benchmarks.

🏆 Nex-N2-Pro beats
✅ Kimi-K2.6: 86% (13/14)
✅ MiniMax: 100% (8/8)
✅ GLM-5.1: 100% (13/13)
✅ DeepSeek-V4-Pro: 92% (11/12)
» Opus 4.7: 45% (5/11)
» GPT-5.5: 30% (3/10)

[codesamplez @codesamplez]

@AnthropicAI The 3x to 52x on a fixed benchmark is staggering. But for open-ended research where the objective isn't well-defined — is the speedup even measurable the same way? That distinction feels like the crux of the whole RSI question.

[codesamplez @codesamplez]

@hwchase17 @Zai_org @baseten @mintlify The markdown/YAML config approach is interesting — does switching from imperative code to declarative files change how you'd handle runtime errors or dynamic behavior? Curious whether the trade-off is simplicity up front vs. debugging overhead later.

[Programmer Humor @PR0GRAMMERHUM0R]

smallQuickFix

[Skyler Miao @SkylerMiao7]

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 😎

p.s. M3 has already submitted a lot of PRs into MiniMax Code.

[Programmer Humor @PR0GRAMMERHUM0R]

thePMIsNotGonnaLikeThis

[Ahmad @TheAhmadOsman]

https://t.co/uRDNr16FHA

[George Lawrence @Georgemummysboy]

😂🤣😂, 🐶

[Nandkishor @devops_nk]

Indie founders only:

[Programmer Humor @PR0GRAMMERHUM0R]

justCodexThings

[Abhishek B R @abhitwt]

Mfs clicking "accept all" on 31,589 Claude Code changes without reading a single line of code be like

[codesamplez @codesamplez]

@karpathy The verifiability + economics framework for jaggedness — do you see those as independent forces or does one constrain the other? High-verifiability domains get the most RL investment yet produce the most visible failures. distribution issue or something deeper.

[Jun Kim @jundotkim]

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!
https://t.co/maWzDJUvsH

[Andrej Karpathy @karpathy]

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.

[Kr$na @krishdotdev]

Minor in Computer Science.
Major in Claude Code.

[Cipher @Cipher_twt]

🗿🗿

[ClaudeDevs @ClaudeDevs]

Claude Code weekly limits are increasing 50%, now through July 13.

Live now for all Pro, Max, Team, and seat-based Enterprise users.

[Charly Wargnier @DataChaz]

just like my vibe-coded app—yeah, it’s buggy, but if it works, don't touch a thing

[codesamplez @codesamplez]

@vercel_dev @aisdk Interesting pattern — how does the web adapter handle auth when running behind a CDN or edge function? Does the cookie parsing work the same way, or does it need adjustments?