Onur Solmaz blog

TLD stands for top-level domain, but if you clicked this post, you already know that.

Note: This post is AI-assisted.

That old macbook with 8gb unified memory or windows gaming laptop of yours can now be your fully local and private AI server Customer data.

Don't sleep on this model everyone, this is SOTA for <= 16GB memory for inference (which is a LOT of people, old M series macbooks, gaming laptops and such)

Weight update to Qwen3.5-9B by Xiaomi Is this the new SOTA for its size?

It's been almost 1.5 years since I started using agents, and I have realized that I went back in certain ways, besides improving in some others I was used to focusing on a single part of the codebase for an entire day.

There is an effect that I call "counterintuitivity bias" When something goes against what you know to be true so much, you doubt yourself like "huh, maybe I am dumb after all" Don't fall for this.

this is officially a competition

OpenAI is rumored to be deprecating Terra I will add one more prediction: *They will have to deprioritize/deprecate Luna as well, near to mid term.

Exciting!

DGX Spark users Make your agents run your inference engines with OOMwrap Protect your machine from freezing up if they accidentally launch something that takes too much memory, like a model with wrong concurrency or context settings Couple this with rfjak…

Looking back at my YouTube channel, I realize this 13 hour long rendering of Euclid's Elements I did back in 2022 got almost 3K views I don't want to think that is 3k people who finished it end to end 😅 Animation voiceover by manim-voiceover, a library I…

We are live demoing Ling 3 Flash on the DGX Spark!

Qwen bros taking too long with 3.8 35b-a3b so people are distilling the larger 3.8 onto 3.6 🤯

SOTA defense against the lethal trifecta?

pi-workflows is now stable-ish again I seem to have resolved most of the issues, if you want to give it a try in v0.17.3 also, I have changed autoimplement to follow a graph pattern which I call "control loop" I believe the pattern is crucial for a lot of…

I am posting a lot of positive things for DeepSeek V4.1 Flash these days But that does not mean it does not have issues It suffers a terminal case of Claudish/RL-ese/whatever you call it Its default output is UNREADABLE.

Minor correction, 10 TB comes with a PRO account, free accounts might not be that much.

This.

It seems OpenAI is about to drop GPT 6 Sol and move the goalpost this week, but still...

A crazy rest of September/October is ahead of us If DeepSeek V4.1 Flash sits between Terra and Sol… Then where will V4.1 Pro sit?

I will be shooting a lot more videos now btw that I have Screen Studio Any suggestions for a good microphone/camera?

Launching https://t.co/SGQepULb6z Front Page 🎉🎉🎉 If you are addicted to local/open-weight models like me, here is a new page to check daily, alongside Twitter and Hacker News Whenever someone here on Twitter posts about a model and it receives enough enga…

Extremely cool

Reminder, we have GPT 5.6 Terra at home (If you have 256 GB memory 😭) At a ridiculous, peanut-sized, 890 KV-cache bytes per token Pinnacle of efficiency by @deepseek_ai And we are just getting started

I made DeepSeek V4.1 Flash play Settlers of Catan against GPT-5.6 Luna/Terra/Sol in 16 games, with different thinking settings DeepSeek was on Novita through Hugging Face Inference Providers DS beats Luna EASY Against Terra, games that finalized end up be…

Btw I had a breakthrough with the data I have here I feel like it is the GPT-3 moment for the fitness industry, personal training, yoga, martial arts, dancing and such Not to imply I have invented a new architecture.

New player has entered the game

.

In the light of recent AI sovereignty concerns, I am repeating this point You CAN own your AI STACK You CAN build and run your own MODELS You DON'T HAVE TO give your DATA to OpenAI or Anthropic which will eventually use it to make your business obsolete I…

@cherry_mx_reds I agree

I trained an AI model on my phone through Telegram Using OpenClaw running on Hugging Face infra: ML Claw It beat DeepSeek V4 Pro on the given task while having 80 thousand times less parameters That's right.

seize the means of computation

DeepSeek V4.1 Flash looks contaminated with public benchmarks.

I want to co-sign this, but I don’t acquiesce to blatant astroturfing I agree with @TheAhmadOsman here

A threshold was crossed with DeepSeek V4.1 Flash, similar to when Claude Code launched, or the last Christmas of Agents.

People who have been running DeepSeek V4.1 Flash on private benchmarks: how does it compare against V4 Flash 0731?

Another deepseek v4.1 flash issue, model started to refuse work around 700k token line, saying "context is gone", and it has no context repeatedly deepseek advertises 1m context, but the usable context with this model is probably still around 200-300k like

4 instances of DeepSeek V4.1 Flash played Settlers of Catan against each other The whole run took 4.5 hours, 77 turns, 634 API calls and cost 5.7 usd (much slower than an average human game, despite 200 tok/s on novita) Red took the lead on turn 13 and was

Not sure if this is chain of thought degradation or regular, but I'm getting this no deepseek v4.1 flash on novita pretty frequently

woah first time i got hit by a mermaid chart in @pidotdev, looks so good!

In the Jacobian conjecture and other recent cases (if not all), agents acted like counterexample monkeys brute-forcing their way into a disproof in a way that does not show the same level of eloquence as a human, by human standards The bar has shifted.

Hold that thought, there is still hope:

Who would like to see similar RL work for training a small model to play Settlers of Catan?

WAIT, THERE IS STILL HOPE

"Fair challenge", "Fair — that's on me", "That error is the whole bug", "Short answer: no.

DeepSeek V4.1 Flash is NOT an LLM It is a hyper-efficient, invasive species designed to displace every other LLM, similar to how Döner displaced all other fast food in Germany As if V4 wasn't cheap and efficient enough, they made it a LOT cheaper 2.3x che…

DeepSeek-V4.1-Flash is available on Hugging Face inference providers through @novita_labs on Hugging Chat and it is FLYING at >180 tok/s I asked it my classic prompt "they say you are sota. prove it", and it created this mandelbulb.

@NoemiTitarenco Says "the smallest model in our new architecture family" 😭

DeepSeek V4.1 Flash weights are out!