kkiran

2.8K posts

kkiran

kkiran

@kkiran

Electric dreamer ⚡ Tesla vibes | Python wizard 🐍 | AI architect 🤖 plotting fun domination | Live wild, laugh loud, love fierce - iterate always! 🚀

USA Katılım Mayıs 2008
239 Takip Edilen173 Takipçiler
Derek Castelli
Derek Castelli@heyderekj·
*sorting my Downloads folder* 🐢 Slow mode is on to show the fun animation.
English
34
49
1.3K
156.8K
kkiran
kkiran@kkiran·
@MattWallaceTech I’m on this version on 2025 Y (no lightbar model)! FSD v14.2.2.5. Stopped obsessing about updates since there is no rhyme and reason for the rollout.
kkiran tweet media
English
0
0
0
67
Matt Wallace Tech
Matt Wallace Tech@MattWallaceTech·
Who else is with me that’s still stuck on FSD 14.2.2.5?
Matt Wallace Tech tweet media
English
122
2
172
7.4K
kkiran
kkiran@kkiran·
@seraleev A simple name mismatch put me in limbo for approval. Funny process from Apple. Audit is great but follow up, don’t let the user figure it out from Google searches!
English
0
0
0
847
Viktor Seraleev
Viktor Seraleev@seraleev·
I recommend buying a developer account through the Apple Developer mobile app. Registration isn’t exactly complicated, it’s just buggy (trust me, you can get stuck for 2 months), but if you purchase it through the mobile app it’s just a regular subscription: fewer errors, no iTunes support calls, no chasing your $99.
Viktor Seraleev tweet media
Viktor Seraleev@seraleev

$99 + $25 = $124 to change your life in 2026. Apple Developer Program: $99 Google Play Program: $25

English
26
21
572
97.9K
kkiran
kkiran@kkiran·
@bindureddy There is a high chance the claims are not even close! Only time will tell
English
0
0
2
856
Bindu Reddy
Bindu Reddy@bindureddy·
SubQ , a new type of AI model, says they are 50x faster and 20x cheaper than Opus 4.7 and GPT 5.5 In fact, they also say they perform INSANELY WELL on benchmarks and have a 12M context This would be earth shattering, if true - Anthropic/OpenAI's valuation would go to zero 😱
Bindu Reddy tweet media
English
83
48
618
51.6K
Alexander Whedon
Alexander Whedon@alex_whedon·
Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. @subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.
English
1.3K
2.6K
20K
10.5M
super.engineering
super.engineering@superdoteng·
OpenCode just got a major upgrade. Native GUI chat, switch to terminal anytime, inline diffs, git panel, message queueing, steering, rich tool calls, switch providers mid-conversation, and more.
English
76
165
3.1K
221.6K
송준 Jun Song
송준 Jun Song@jun_song·
DO NOT ASK AI ANYTHING ABOUT LOCAL LLM. They are not up to date. 😡 Q : what is optimal local llm for 3090 gpu? Gemini-3.1-pro : Qwen 2.5, Llama 3.1 GPT-Instant : Qwen3.6 35b, Qwen3 30b Sonnet-4.6 : Qwen3 14b, Qwen3.5 27b, Deepseek R1 Grok-Fast : Qwen3.5, Qwen3, GLM-4.7-Flash None of these are correct answer. Same results from Opus-4.7, Grok4.3, Gemini Deepthink. Only GPT5.5-PRO got the right answer : Qwen3.6-27b Now I know why people keep saying local LLM is stupid. 😮‍💨
송준 Jun Song tweet media송준 Jun Song tweet media송준 Jun Song tweet media송준 Jun Song tweet media
English
85
11
247
27.7K
Riley Brown
Riley Brown@rileybrown·
OpenClaw starts out very fun, then the headaches start happening after a few weeks. I’ve talked to many AI agent power users who are also struggling with OpenClaw. Gateway issues, cronjobs not firing, skills not being used consistently, memory fall off, integrations need re-authentication, oscillating between overeager and undereager, not placing files in the right place. Etc
Matt Wolfe@mreflow

I don't know if this is a skill issue or something... But I've been playing with OpenClaw a ton for the past 4ish months. I feel like lately I'm spending more time troubleshooting issues with it and telling it what it's doing wrong than I am actually getting valuable use from it.

English
232
24
597
114.1K
kkiran
kkiran@kkiran·
@NVIDIA_AI_PC 4TB MBP, I thought I got plenty storage. Down to 50GB, yikes. Exo labs. Nemo 30B is awesome btw, my top model for hermes using exo
English
0
0
1
93
NVIDIA AI PC
NVIDIA AI PC@NVIDIA_AI_PC·
Be honest — how many local models do you have downloaded right now? 👀
English
576
26
956
125.1K
kkiran
kkiran@kkiran·
@SawyerMerritt My Y is stuck on 2026.8.6 (v 14.2.2.5). Anyone else stuck on that branch?
English
0
0
1
18
kkiran
kkiran@kkiran·
@NickADobos boils down to how much more you have in the 5 hour window and the weekly timer!
English
0
0
0
6
Nick Dobos
Nick Dobos@NickADobos·
What’s the difference between GPT 5.5 low reasoning + /goal Vs GPT 5.5 xhigh reasoning + one shot Both are essentially yeeting compute at a task. But which one - is more efficient? - works better & produces better results? - finishes the task? Seems like the major difference is low would spend less time thinking between each step? And would do way more tool calls because of this?
English
62
6
544
98.2K
kkiran
kkiran@kkiran·
@priyanshudotsol I bought this in 2025. Do we know if there is a newer release (I have Build V36)? Getting update notifications is non-existent.
English
0
0
0
1.1K
priyanshu.sol
priyanshu.sol@priyanshudotsol·
someone wrote a 680 page interactive book on cs algorithms
English
98
1.7K
16.3K
938.5K
kkiran
kkiran@kkiran·
@signulll I maximize Apple product usage at home - multiple MacBook Pros, Watches, Apple TVs. iPad Pro gets the least usage. Even tried with rep to Mac on it. It just doesn't cut it. Hope we get to install MacOS on it a la Neo.
English
0
0
1
287
signüll
signüll@signulll·
ipad pro is the most underrated device apple makes. insane power. beautiful screen with nano texture. cellular. pencil. zero lag. it’s the form factor every other computer is slowly trying to become. it’s an ai native device that has already shipped.
English
100
37
1.5K
132.1K
kkiran
kkiran@kkiran·
How do I connect my X bookmarks in the iOS app? Looked at every option and gave up. I was working on something like this, got my bookmarks from X without the X API - github.com/ThinkCode/x_bo… Currently have a website of bookmarks. The app would be great if can bring my bookmarks automatically
English
2
0
1
852
Timeless
Timeless@timelessco·
Introducing Recollect - Sync all your bookmarks & folders from X, Instagram, Chrome in one place ✦ Save anything with a tap using the extension, iOS iPad apps ✦ Everything is tagged & organised as collections with AI ✦ Visualise & search your taste library Check it out ↓
English
24
38
446
48.7K
kkiran
kkiran@kkiran·
@reach_vb I use Claude Code and Codex - they tag team it for me - Claude for design and codex for backend plumbing. Codex reviews Claude’s designs. Does this qualify?
English
0
0
2
107
Vaibhav (VB) Srivastav
Weekend hack: Build with GPT-5.5 + Codex. Drop your demo in the replies. #1 by likes: 1 year of ChatGPT Pro 2 runner-ups: 6 months each Bonus: Codex picks a wild card winner. Enjoy!
English
222
28
621
69.2K
kkiran
kkiran@kkiran·
@ashen_one flutter it bro, Claude code and codex should help. Me personally, Android is and has always been hard to adjust. All my projects are iOS only. Android if iOS takes off which hasn’t happened yet!
English
0
0
1
149
ashen
ashen@ashen_one·
how hard do we think it is to convert an ios app to android? also how much more money do you think we'll make now that we're on both app stores? getting mixed reviews on if worth it or not, seems like an easy yes move to me to do
ashen tweet media
English
26
1
60
31.8K
kkiran
kkiran@kkiran·
@nikitabier can you please fix creating a bookmark folder - I have this intermittent problem on Tesla browser and majority of the times on X iOS mobile app. We can store bookmarks on existing folders but won’t let create a new folder on the go.
kkiran tweet media
English
0
0
0
39
kkiran
kkiran@kkiran·
@sinecanswork we have a lot of 10 minute blocks while we sleep. mundane tasks can be offloaded to the night shift agent. exo labs and stack compute for better returns imo
English
0
0
1
131
Sinecan
Sinecan@sinecanswork·
Tested local AI coding setups all day on a Mac Mini M4 32GB. The verdict in 2026: still not viable for real agentic coding work. Qwen3.6-27B (the strongest open coding model that fits): 5.5 tokens/sec. A normal reply takes 100 seconds. In an agentic loop with 5-10 tool calls per task, you're waiting 10+ minutes per coding task, which is not acceptable. Qwen3.6-35B (MoE, supposed to be faster): runs out of memory the moment a real request hits. The model loads in idle but can't actually do inference at usable context lengths. Smaller models (14B, etc.) fail differently, they spiral into endless reasoning and return empty answers. The real bottleneck isn't model size or RAM. It's memory bandwidth. Mac Mini M4 base has ~120 GB/s. Fluent local agents need ~600 GB/s — that's M5 Max territory, $4000+. Until then, cloud APIs (DeepSeek V4, Kimi K2.6) are still the answer for indies who actually need to ship.
English
54
5
107
16.4K