Nilesh

Ehe...

Obviously what I post are my personal opinions

[Nilesh @AzuLa9713]

Made a fork of @mattpocockuk’s Sandcastle project.

It’s called Narukami Shrine, because why not.

This fork is focused on Codex subscription usage + Linear as the tracking provider. Linear MCP is required for the default workflow to work properly.

One change I made: reviews use Codex’s built-in review flow by default instead of always passing a review prompt. You can still provide one if needed.

https://t.co/zSwX7Zuua5

PS: If you’re using Claude Code or a non-Linear issue tracker, I strongly recommend using the original Sandcastle project instead.

[Theo - t3.gg @theo]

Oliver Tree will be mostly remembered for memes. I hope we don't forget that he was a genuinely great artist too.

Feels like a good time to share his debut track "Forget It" (w/ Getter).

RIP Oliver. You brought joy to millions in your short time here. 💙

[‏ً @omgsidewalks]

Dear restaurants,

Bring back the physical menus. Nobody wants to be scanning QR codes when they're hungry.

Regards: The whole world.

[NewsWire 🇱🇰 @NewsWireLK]

Sri Lanka will establish a massive 16‑storey Heart Treatment Centre with advanced facilities at the National Hospital this year, at a cost of Rs. 12,000 million. Health Minister Nalinda Jayatissa said construction will begin in 2026 and finish within three years. He further revealed that discussions are underway to set up a Stroke Unit.

D: https://t.co/lgsi508tei

[Nilesh @AzuLa9713]

@nisalrenuja Apparently they have whitelisted pretty much all known speedtest tools, but if you try with something unknown or DIY, you will see upload speeds are downright garbage. (Im on 5900 plan)

[Uncle Bob Martin @unclebobmartin]

if anything you want your agents to do is deterministic, such as managing a queue, or sorting a list, create a script for the agent to use. Agent's don't do deterministic things well. It's our job to force determinism upon them.

[ThePrimeagen @ThePrimeagen]

just never forget that the devs who yap about AI being the best thing ever all day never really knew how to program well to begin with.

They are idiots telling you that the world is solved (charitable read) or worse, they are selling you something and are attempt to deceive you.

This is why we see the same cycle every time. Opus 4 = God's gift to humanity to OMG its utter trash within a few months. The same thing happens with every model release because these people don't even know what dev is. They are larpers.

I believe this is what Geohotz meant when he: "I’m calling it now, the adoption of AI agents into software development will be one of the most costly mistakes in the field’s history."

[barc(ell)ona💃💃 @cantverstopim]

2026 as a verstappie summed up

[🐊🐊🐊 @wherestappen]

2026 season notable rivalries

[Lewis Hamilton @LewisHamilton]

REMEMBER WHO YOU ARE

[Kanye East @FuckedUpYogis]

Dude he literally running New York like the average joe in a movie who gets elected into office as a gag and then fixes everything simply because he is not a politician and an earnest regular guy.

[Nilesh @AzuLa9713]

@tanujDE3180 IM SORRYYYYY

[Nilesh @AzuLa9713]

How Sri Lankan bikes and tuktuk lines up in every traffic light

[まだ面白い @madaomoshiroi]

整列し直す空き瓶達が見てて可愛い

[Asa @xAsamoahx]

I don’t know if he wanted me to write about someone else’s dog 😂

[Nilesh @AzuLa9713]

@zeeg Does this cover fast usage as well?

[ClaudeDevs @ClaudeDevs]

As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models.

Here’s what this means for you:

Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error.

On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models.

We know this is a disruption to your workflows; we appreciate your patience and support.

[Kimi.ai @Kimi_Moonshot]

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!

🔷 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.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.

⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.

🔗 Kimi Code: https://t.co/uvoSJKyGCY
🔗 API: https://t.co/EOZkbOwCN4