Theo - t3.gg
@theo ·
I should clarify: this is over the internet, not via computer use.
If I turned off my laptop, I can still control my other machines via my Grok Bot on my phone.
Back
AI posts
AI posts
People and companies shaping AI. Filter your watched accounts, catch up on recent posts, or find the most liked and viewed.
Compiled by the Toolstash team · Updated
209 watched accounts · 2977 matching posts · Showing up to 3,000 recent stored posts. Counts are snapshots, not live X totals. This page refreshes every minute while visible. Last collected .
@levelsio@levelsio ·
Everything I do runs on my VPS servers
The only interface is Termius SSH and then Claude Code on the server
All my businesses but also my health stuff, calories, sleep etc. all my data is pulled into there
Then the output is either chat responses from Claude Code on the server or websites it builds
So I can ask "did magnesium last night improve my sleep" and it pulls my sleep from WHOOP, nutrition from my food tracker, and even bedroom temperature and air quality data to check confounding factors etc
All server side!
kache@yacineMTB ·
Deepseek flash 1017 is genuinely a better model than any of the garbage that OpenAI is peddling
Peter Gostev@petergostev ·
This is a little chart I made 2 years ago (before GPT-5 was launched).
GPT-5 era muddied the waters a bit with heavy RL, but we are definitely following this cycle with GPT-6 now.
Dean W. Ball@deanwball ·
This is the first time an Artificial Analysis ranking has even roughly approximated my own subjective rankings of models.
Gabriel Chua@gabrielchua ·
"benefits all means intelligence for all"
Pavel Rabtsevich@p_rabtsevich ·
2 subs and both finished, nice limit reduction. from the previous last week where we had it unilimited, now even 2 x20 is not enough
anthropic saw me paying for 2 and thought "why stop there" 😀
Mia@MiaAI_lab ·
Important updates and fixes have been pushed to DeepSeek V4.1 Flash for 4x DGX Sparks ⚡️
This update includes 7 community PRs!
Performance - Chats with images: resending a 35-image chat dropped from 20 s to 1 s (20x faster) - No more waiting: a short question asked during a long 51k-token prompt now answers in 0.3 s instead of ~13 s - CPU use per machine dropped from ~310% to ~0.2% (about 12 CPU cores freed) when on idle
More reliable - Long prompts no longer time out clients (a keep-alive signal every 15 s) - Safer start/stop scripts - The test tools can’t report a false “pass” anymore
Also, /metrics now shows how many prompt tokens came from the cache (prompt_tokens_cached_total), so dashboards can tell cache hits from real prefill work
Thanks to @easthambuilds, @krunkosaurus, @uchkw, Manuel (manuel1618), and SvangenStudios, plus upstream TensorFold work by @jayleaton, @ashxhart and @BobClawblaw 🙏
Get it here: https://mia-ai.net/models/DeepSeek-V4.1-Flash-1017-4x-DGX-Sparks-TensorFold
- @levelsio
@levelsio ·
+16 min REM if you compare to last 30 days
But again only directional, not proven yet until it keeps happening!
- Theo - t3.gg
@theo ·
Day 29/
You can now control your whole fleet through a single MCP server in T3 Code. Here's me spinning up 8 threads on different machines via Grok Bot.
Marc Lou@marclou ·
You can't lose in entrepreneurship.
You either win, or you learn.
Gergely Orosz@GergelyOrosz ·
Example of the impact of "good" AI:
Speeding up processes that seemed IMPOSSIBLE to speed up in the past! So challenging timelines from pre-AI.
These will include doing away w decades-long assumptions like "it takes at least 2-3 days for Legal to review contracts over $100K"
- Theo - t3.gg
@theo ·
I think I found the perfect analogy for how to code with agents
- @levelsio
@levelsio ·
+30min REM sleep with magnesium glycinate!
It's just one day so too early to conclude but interesting direction
And I did get magnesium dreams but not bad dreams or nightmares at all, just normal but I can't remember them
😴
Tom Dörr@tom_doerr ·
Add 42 video editing tools to Claude Code, Cursor, and MCP clients with npx ffmpeg-skill.
- Gabriel Chua
@gabrielchua ·
1. what
Paul Couvert@itsPaulAi ·
That’s very very impressive
This minicpm-ocr model is 100% open source and has only 1.3B parameters… while being
- capable of extracting text/handwriting - up to 128 pages per minute (!!) - way more accurate than others
And it has a Jev variant with just 2B parameters and a performance approaching models literally 200x bigger!
Open source local models are winning even when it comes to ocr!
GitHub: http://github.com/OpenBMB/MiniCPM-OCR Hugging Face: MiniCPM-OCR 1.0 http://huggingface.co/openbmb/MiniCPM-OCR-1.0 / MiniCPM-OCR Jev http://huggingface.co/openbmb/MiniCPM-OCR-Jev
Tibo@tibo_maker ·
leaked footage: Anthropic HQ
Dario pitching Wall Street
- Theo - t3.gg
@theo ·
The trick is to run so fast that you don't know how far ahead you are
nicksaraev@nicksaraev ·
There's a serious risk this occurs across the world.
Which is why you should buy first aid kits, food, and water now.
Vals AI@ValsAI ·
About half of U.S. adults now use AI chatbots, and questions about visas, work permits and immigration status are among the most consequential they ask. Can the models be trusted?
With the Talent Mobility Fund, a program of @RenPhilanthropy, we are releasing Immigration Bench to test whether frontier models are able to answer these high-stakes questions.
Carmine Paolino@paolino ·
Can't wait to have RCC in Berlin next year.
We'll have a special @berlinrb_org the day before!
- Theo - t3.gg
@theo ·
I'm not gonna lie, this puts us in first place by default. Nobody has this working end to end yet.
- @levelsio
@levelsio ·
At least 85 people this year died from Spanish train accidents, and likely it will grow to 100 at the end of this day
Very tragic and this makes Spanish trains one of the most dangerous modes of transport now
~100x more dangerous than flying commercial
~40x more dangerous than non-Spanish trains
And every trip is nopw as dangerous as jumping from a plane and skydiving
Two highly deadly train accidents in one year, that's so extreme and unlikely that it makes it at as dangerous as flying one of the most deadly airlines in the world, the Nepalese Yeti Airlines that keeps crashing due to the mountainous terrain
Pretty exceptional in a bad way
- Theo - t3.gg
@theo ·
Day 28/
Julius cooked harder than I thought.
Multi-machine orchestration has been achieved internally.
One thread, multi-model, multi-harness, multi-app, multi-os, multi-machine, multi-network.
We're just getting started :)
Peter Steinberger 🦞@steipete ·
OpenClaw’s web UI now works offline and uses a smart websocket compression/reconnect logic.
Been flying to Vienna today and got plenty work done, despite spotty airplane wifi.
jason@jxnlco ·
Unironically mission aligned right
Matt Pocock@mattpocockuk ·
Banger PR
Summary, evidence, merge danger on point
A great example of my /pr skill in action
https://github.com/mattpocock/course-video-manager/pull/2399
- Peter Gostev
@petergostev ·
Astra was a great model but expensive, GPT-6.1-Sol was only slightly worse, but 80% cheaper, then GPT-6.1-Terra is slightly worse than Sol, but it is 50% cheaper.
So in <2 months, we got a model that it only somewhat worse than a model that is 10x more expensive. Good stuff.
Nathan Lambert@natolambert ·
I feel a need to defend the AAv5 index and open models at the same time. Benchmarking is messier, more opinionated, and trickier than most people give credit to.