Dan Kimani retweeted
RAM is the new bottleneck. Every Node.js process is fighting for memory: containers, serverless, cloud bills, k8s limits. And here's the maddening part: V8 can use half the memory with one flag, and almost nobody turns it on.
Dan Kimani retweeted
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: platform.minimax.io
M Plan: minimax.io/m-plan
MiniMax Code for desktop: agent.minimax.io/download
Dan Kimani retweeted
🌴Announcing TanStack Table V9🌴
Now Stable!
After more than two years of development, TanStack Table V9 lays a new foundation for years to come, with a tree-shakable plugin architecture, state management powered by TanStack Store, new features, major performance improvements, hundreds of bug fixes, and more.
Dan Kimani retweeted
✨🇨🇳 These are next-generation smart blackboards in classrooms across China.
While the US debates how to address homelessness, China channels public resources into education — investing in the next generation instead of wars.
When tax money flows to people and their future, it lays the groundwork for long-term progress.
Here's my current stack
----------
Models:
1. GPT-5.4 - Research + Programming + Parchi + OC
2. Kimi-K2.5 - Frontend Dev + Computer Use + Parchi
3. Opus-4.6 - Writing + Review GPT + Fallback
4. Gemini-3.1-Pro - Writing + Research + Reviews
5. Secret Model - Very fast + Devops + Cheap
-----------
Harnesses:
1. Codex - It's the highest value play rn
2. Droid - Best multi-model harness & missions
3. Parchi - Browser use (I genuinely think this is the best one on the market)
------------
Apps:
1. Codex / Opencode - Kitty and OC for OSS models
2. KittyLitter - Mobile Codex access
-------------
Terminals & IDEs:
1. Cmux - When I need to read while I prooompt
2. Zed - When I want to read the code
3. Ghostty - GOAT simple terminal
--------------
Browser:
1. Brave - I am open to Helium if u wanna tell me what makes it better
--------------
Infra:
1. Tailscale - Securely linking all your devices
2. VibeProxy - Use your subscriptions anywhere
3. Amphetamine - Keep computer awake 24/7
--------------
Quality of life:
1. Superwhisper - AI voice transcription
2. Raycast - Clipboard / Calculator / shortcuts
3. OBS - I record a lot of stuff and don't pay :p
Dan Kimani retweeted
Double the Density. Half the Memory (with James Snell) xitter.gq/i/broadcasts/1nGnRYRyv…
Dan Kimani retweeted
Rich clients ask:
- What’s included?
- What’s the process?
- How fast can we ship?
- What does success look like?
Poor clients ask:
- How do you justify this?
- Break it down hourly
- That’s way too high
- Others told me lower
That’s not curiosity, that’s resistance.
Dan Kimani retweeted
If you are struggling with ACNE,
Stop listening to mainstream advice.
They will mislead you to sell you drugs, injections, creams, soaps, lotions and towels.
Read this thread and have an acne-free face.
#FoodFriday
Dan Kimani retweeted
Major open source wins this year:
- DeepSeek cracked cheap long context for LLMs
- Qwen dropped the best vision model in the world
- Llama 4 Scout arrived with a 10M context window
- Minimax M2 delivered sonnet 4.5-level performance at 8% of its price
- GLM 4.6 brought a 200k token context window and performs with Sonnet 4
- Kimi k2 thinking outperformed GPT-5 and Claude 4.5 Sonnet on several benchmarks while being 10x cheaper than GPT-5 and 20x cheaper than Sonnet 4.5
The gap between closed and open-source AI is closing fast.
Dan Kimani retweeted
for every closed model, there's an open source alternative
sonnet 4.5 → glm 4.6 / minimax m2
grok code fast → gpt-oss 120b / qwen 3 coder
gpt 5 → kimi k2 / kimi k2 thinking
gemini 2.5 flash → qwen 2.5 image
gemini 2.5 pro → qwen3-235-a22b
sonnet 4 → qwen 3 coder
Dan Kimani retweeted
whoa. I just found a way to properly infer recursive types in z.object() — no casting, no z.lazy(), no scopes/registries, no special syntax.
i've been trying to do this for literally years
Dan Kimani retweeted
I don't understand why squash merging is not the default on GitHub. The other options make no sense, and just slow things down.
Similarly, it's confusing that people *still* use `git merge`. It makes everything so complicated. Always rebase, never merge.
Dan Kimani retweeted
Enhance your terminal experience in @code by enabling this one setting ⚙️
The terminal.integrated.suggest.enabled setting, currently in preview, surfaces rich completion support for your terminal.
Dan Kimani retweeted
This coming Saturday Kirwara hospital Gatanga, Muranga County Government will launch mobile Dialysis services mounted on a truck.
To reach patients in remote and rural areas of our county.
Dan Kimani retweeted
Meet a multilocationist working for William Ruto. This woman is both Embu, Maasai and so far Kisii. She has the capacity to be mamamboga, Tea Kiosk owner, house wife and Posho Mill Owner. She simultaneously lives in 3 different counties (so far). Yes, she meets the president..
Dan Kimani retweeted
Here’s the message I was passing. Let’s design new grassroot mobilization tactics.
When the Cause is Just, Conquer We Must.
#ConquerWeMust
#RutoMustGo
#RutoMustBeStopped
Dan Kimani retweeted
Guys, before we continue with our movement, we need to address the issue of missing people. The loud ones are visible wakikua arrested. Kuna smallwigs and small names wanaenda missing never to be found. Kama Gibson Kariuki etc.
#RutoMustGo





























