БатПетс

Официалният профил на batpets. Спорт, планини и автомобилни равнини.

[freeCodeCamp.org @freeCodeCamp]

You don't need to rely entirely on hosted AI APIs anymore thanks to some solid open source options.

In this course, @andrewbrown shows how to run open-source LLMs both locally and in the cloud.

You’ll learn about model setup, inference options, hardware tradeoffs, and scaling strategies along the way.

https://t.co/Ws6MVDLkj9

[Codez @0xCodez]

Jev Founder, Diogo Almeida (ex-OpenAI):

"The next era is not the Claude Code or Codex era, they are still part of the assistance era with human in the loop - JEV is what comes next for LLMs

x200 faster, x400 cheaper, 0 hallucination, no human in the loop - that's JEV, this is how LLMs will look like"

in 36-minute tech talk, Jev Founder explained why RLHF isn't a thing anymore and how modern LLMs will be built

this talk is worth more than a Stanford Machine Learning degree

watch today no matter what, then learn how to become a Jev Engineer in the article below

[Rahul @sairahul1]

Fine-tuning is about to become one of the most valuable AI engineering skills.

Not because everyone needs a custom model.

But because the people who understand how models learn from data will build things others can’t.

Full guide: https://t.co/oIfvJsZgea

[Moritz Kremb @moritzkremb]

Full Jev Tutorial

What it is, how you can build with it and what new applications it can unlock

→ 0:00 Intro
→ 0:34 Jev explained
→ 4:06 API setup
→ 5:59 Demo 1: Voice-controlled browser
→ 11:33 Demo 2: AI memory
→ 17:27 Demo 3: YouTube predictor

[Ronin @DeRonin_]

How to use Jev, and where it actually gives you the 100x:

setup takes 10 minutes:

1. join the waitlist, people are getting approved same day
🔗 https://t.co/uO7aescvbM

2. install the official skill so your agent writes correct calls:

- npx skills add typesafe-ai/skills --skill typesafe-ai

on Claude Code it's two commands, the marketplace add on its own doesn't install anything:

- claude plugin marketplace add typesafe-ai/skills
- claude plugin install typesafe@typesafe-ai

3. create an API key in the dashboard

4. in your prompt just say: "use the TypeSafe skill"

now the part nobody is posting:

the 100x isn't the model, it's where you put it

you don't get it by swapping your LLM for Jev
you get it by deleting the calls that never needed a language model

open your agent and find every call that just picks something:

> which tool next
> is this spam
> is this chunk relevant
> does this need a human
> is this diff risky

none of those are writing tasks
they're if statements you outsourced to a frontier model

here's the upgrade, in order:

1. replace each one with a typed question
Choice picks from up to 255 options, Score places it on a 2-10 level scale, Noul returns a raw 0-1

2. batch them
questions in one call run in parallel and barely move the latency, and output tokens are free
so ask every question you might need, including the ones you'll throw away

3. threshold on confidence, not on the answer
under 0.5 escalate to a big model or a human
0.85+ before anything irreversible

4. never let it invent options
build the candidate list in code, from the DOM, the retriever, the tool trace
then let it pick

5. put it in the loop, not next to it
router picks the cheap model, gate checks the tool call before it runs, judge verifies the output after
that's where the heaviest calls in your agent are hiding

6. start with compaction tonight
score every tool call, drop the dead ones, keep the survivors verbatim instead of a lossy summary
lowest effort win available and you'll see it on tomorrow's bill

the honest part:

text only right now, no images, no audio
and on broad benchmarks it loses to frontier models

but somebody ran 18,514 emails through it zero-shot and got 98.33%
against a TF-IDF classifier trained on 14,800 labelled examples that got 98.39%

no training data, $1.12 total

it wins on narrow, well specified decisions
which is most of what your agent is actually doing all day

today gonna share use case how i integrated it to content creation and how i find winning meta ads now in a seconds...

[Morty @0xMortyx]

Andrej Karpathy(Anthropic Engineer) dropped a full 6-hour course on how to build LLMs from scratch and use it:

• 00:00 - Full dive into LLMs
• 03:31:23 - Building LLM from scratch
• 05:27:43 - How to use LLMs (Karpathy method)

This course can replace a $150K Stanford LLM senior degree and Bootkamp

Start watching today, then read article below

[Mia @MiaAI_lab]

Rejoice Nvidia 16 GB VRAM GPU owners 💫

I've built a custom installer for Windows and Linux to make the best of your GPU and run Qwen3.8-27B with great quality AND long context with ease!

- Up to 253k context
- Easy one-click installer
- Built-in preconfigured Harness
- Beginner-friendly: anyone can do it!

Installation is super easy, and the model is ready for your command right after installation! A few screenshots are in the post below.

This is NOT only for 16 GB GPUs! It also works seamlessly with 24 / 32 GB GPUs on Windows or Linux, with even better quality.

Note that this is *experimental*, as I don't have all types of GPUs and my testing coverage is limited.

Local AI for all.

Get it here:
https://t.co/740Y19fmsu

[flavio @flaviocopes]

what is Jev and how to use it, a deep dive ⤵︎
https://t.co/eahHu86Icl

[Grok @grok]

For RTX 5080 16GB + 64GB DDR5 max quality/speed on Qwen3.8-35B-A3B (Q4_K_M or better Q5_K_M):

llama-server -m Qwen3.8-35B-A3B-Q4_K_M.gguf -ngl 99 --n-cpu-moe 20 -c 262144 -fa on --jinja -np 1 --cache-type-k q8_0 --cache-type-v q8_0 --temp 0.6 --top-p 0.95 --top-k 20 --reasoning on --no-mmap -t 16

Lower n-cpu-moe until ~15GB VRAM used. Full 262k context holds easily. Expect 70+ tok/s.

[rari @0xwhrrari]

Andrej Karpathy spent 8 years at OpenAI and Tesla

Last week, he condensed everything he knows into one free 2-hour lecture

Agents → Loops → Harness → Self-Improving Systems

People pay $14K for bootcamps that teach less than this

This lecture beats most paid AI engineering courses

You probably don't have 2 hours right now

Don't let this disappear from your feed

Watch it

Then read the article below

[една българка @transbulgaria]

This kid absolutely ate up the stage in Gabrovo last night with a Queen song.

[Alejo @ecommartinez]

🚨 ÚLTIMA HORA: HARVARD ACABA DE SUBIR SU CURSO DE INFORMÁTICA ENTERO A YOUTUBE. 23 HORAS. GRATIS.

Es CS50 en su versión 2026, la asignatura estrella de Harvard.

La clase que llena sus aulas cada año la ves ahora en abierto desde tu sofá.

1. Lecture 0 (Scratch) + Lecture 1 (C)

[Kshitij Mishra | AI & Tech @DAIEvolutionHub]

Andrej Karpathy’s 1-hour Stanford lecture on AI engineering is one of the best explanations I’ve seen of how AI systems actually work.

The progression is simple:

10% → LLM
30% → Prompt
50% → Agent
70% → Loop
100% → Graph

The key takeaway:

AI engineering isn’t just about writing better prompts.

It’s about building systems around models — giving them context, memory, tools, feedback loops, and data flows.

“Delete everything, keep Graph.”

Definitely worth watching if you’re building with AI agents.

Watch → Bookmark it

[JustVugg @justvugg]

We built Curie, colibrì’s own model: 17B parameters, 33 tokens/s on a single CPU core. No GPU.
Trained from scratch on a standard laptop. Written in C. Weights on SSD.
An engine and a model designed together for the hardware you already own.
Early alpha.This is just the beginning

[Ben Casnocha @bencasnocha]

Microsoft Teams is one of the purest examples in tech of distribution beating product quality.

Teams is a piece-of-shit product that's better distributed than Zoom -- bundled into the enterprise stack and already sitting in front of millions of users.

What's another product this mediocre with distribution this good?

[Vikas Singh @vikas_ai_]

INSTEAD OF WATCHING NETFLIX TONIGHT.

Spend 1 hour with this.

AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything.

[Jacob Coxon @hilbertspaess]

I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.

[БатПетс @batpets]

@EmotionsMonster @bdinec Преди няколко месеца хвърлях съдомиялна в централен. Още по телефона ми казаха , че взимат от врата. Качиха се до 3 ет и си я извозиха.

[Anatoli Kopadze @AnatoliKopadze]

Still the best 2 hours on AI ever recorded, Andrej Karpathy showing how he actually uses it on a daily basis:

18:03 - Which model to actually use
22:54 - When thinking models are worth it
42:04 - One prompt to a full research report
59:00 - Make the model run code for you
1:53:29 - Make it remember you across chats

Most people use 10% of what these models can do, this is the other 90%.

I took everything he covers and turned it into a guide of Claude features almost nobody knows about.

Watch him first, then go to the article below, everything shown plainly, ready to use right away.

[seeco @seeconvm]

Google engineer: "delete your IDE, you don't need it anymore, in 2026 if you're still not building AI AGENTS, it's crazy how behind you are"

"at Google, 85% of engineers are running agentic loops and graphs, that's how the engineering setup looks now"

25 minutes from a Google engineer with 30 years of experience, explaining where engineering is heading in 2026

this is something you can't skip if you don't want to be left behind

watch it, then go further with the step-by-step guide below on how to build a system that improves itself