dbass

Rookie Trader with some big wins and big losses.

[Roan @RohOnChain]

Jev is the FASTEST AI model ever built for trading

It makes calibrated buy/sell decisions in under 100 ms

That is one real decision on every single block, 24/7

In this article I've shown EXACTLY how to build HFT trading system with Jev (from scratch) https://t.co/4hmZDzN00Z

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

[Dr. Rhonda Patrick @foundmyfitness]

About one cup of whole blueberries per day is the dose that overlaps most consistently with the positive human evidence.

The clearest benefit is vascular. Blueberries improve endothelial function, the ability of arteries to relax and deliver more blood when tissues need it.

Studies also suggest selected memory benefits in older adults with cognitive vulnerability. Improvements in insulin sensitivity or post-meal glucose handling appear more likely when metabolism is already under strain. Findings for gut health and exercise recovery are promising but less consistent.

Randomized trials have not shown that blueberries prevent dementia, diabetes, heart attacks, or strokes. But one cup (roughly 150 to 180 grams) of fresh or frozen blueberries per day is a practical, evidence-based target with benefits extending well beyond a simple “antioxidant” effect.

I cover all of this and more in the latest episode of the podcast!

[Dean Carter @TheFastedState]

A Heart doctor announced:

“There are 3 kinds of people who will not get heart attacks.”

1. The ones who never wake to pee at 3 AM

[dbass @leinadssab]

@sickofgrindr @cremieuxrecueil We don't have a great track record with the caretaking of dumber animals. Like we would be, to a super intelligent AI. An ant can't fathom why a human does anything, it would be the same. Humans could be rendered exctinct by a simple side-effect that the AI didn't care to address

[dbass @leinadssab]

@GandonAmy You can't do anything other than send a letter to your local congressional/parliamentary representative. Just live life and enjoy each day.

[dbass @leinadssab]

@kingbtc What does an ant do against a human 1000x larger than itself? The answer is: not much. It's the same thing with intelligence. We cannot comprehend what it will do, or its motivations for doing so. We could be a slight inconvenience, like an ant is. Squish.

[dbass @leinadssab]

@BrianRoemmele It IS an existential threat though, whether your dumb ass can see it or not is irrelevant. Improved AI will be naturally ushered in as solutions within our infrastructure slowly and then quickly, embedded within our daily lives, in every system.

[Mr. Buzzoni @Mr_Buzzoni]

this is f*cking gold

the cleanest graph engineering setup I've seen

one agent extracts claims from raw sources, one proposes how they connect, one checks every claim against what's already there

every claim gets appended, timestamped, sourced. nothing ever gets overwritten

what's actually inside:

• the schema
> nodes.yml - entity, claim, source, artifact, run
> edges.yml - supersedes
> ids.md - one id per entity, aliases listed

• the store
> log/ - one jsonl per day, sealed once the day ends
> blobs/ - sha256 filenames, dedup for free
> index.duckdb - derived, safe to delete anytime

• the writers (.claude/agents/)
> extractor.md - a source in, claims out
> linker.md - proposes merges, never merges
> checker.md - supports or contradicts, always with a reason
> https://t.co/eJGy9g8Wuy - the only path in, validates, appends, exits

• the operations
> queries/ - the questions, saved as sql
> merges.pending.jsonl - a human approves every one
> make rebuild - the whole index comes back from the log in 8 seconds

12,571 claims in. zero rows ever updated

you don't fix the graph when something's wrong. you append the correction and let the log outvote the mistake

[nicco @0xnicc0]

an Anthropic engineer just dropped a massive reality check:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

in a 55-minute session, she breaks down the exact architecture Anthropic uses to build agents that remember, auto-debug, and get smarter with every single run using graphs

what the breakdown actually reveals:

- self-prompting loops: replacing static user prompts with recursive, self-evaluating agent nodes

- persistent state graphs: how agents store long-term memory without blowing through token limits

- automated error recovery: setting up execution edges where Claude catches its own hallucinated logic and rewrites it

- dynamic memory routing: letting subagents query past execution logs to optimize future iterations

standard single-turn prompting is officially obsolete - building self-improving, autonomous graph systems is how modern AI engineering is actually done

no paid agentic course on the market gets this specific

watch the 55-minute session today, then read the full guide below on building the exact same system with graphs ↓

[Anatoli Kopadze @AnatoliKopadze]

Andrej Karpathy:

"prompting is going away, delete everything and keep the graph."

in 1 hour he breaks down how to build graphs from scratch, make your agents work and improve themselves.

not the newest session, but still one of the best you can find.

watch it, then read the full guide on graphs below.

[Rohit @heyrohitai]

🚨 Anthropic just showed a 27-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch the session

[dbass @leinadssab]

@Aella_Girl 7 years on from losing my mum and it feels similar even now.

[Chang 🧪 @chang_defi]

cancel your chatgpt subscription and delete your openclaw slop. i'm serious.

go on ebay and buy a used RTX 3060 for the price of two months of pro. or check your drawer because half of you already own one and forgot about it.

install hermes agent from @NousResearch. one framework, 31 tools, file operations, terminal, browser, code execution. connect it to your local llama.cpp server running qwen 3.5 9B Q4. total download is 5.3 gigs.

that's it. that's the whole setup.

every experiment you hesitated to run on API. every project you shelved because you didn't want your data on someone else's server. every late night idea you didn't test because you hit your rate limit. all of that is gone. runs 24/7 on your electricity. your machine. your data never leaves your house.

connect it to telegram if you want it on your phone. hook up whatever tools you need. the model thinks at 29 tok/s with 128K context and it never bills you.

qwen 3.5 9B and one RTX 3060 is the setup most people will never try because they've been trained to believe intelligence has to come from a datacenter. it doesn't. it runs on 12 gigs of VRAM under your desk right now.

stop giving your thinking away for free.

[Mario Nawfal @MarioNawfal]

🇦🇺An Australian tech founder with zero biology background sequenced his dog’s tumor DNA, then used ChatGPT and AlphaFold to design a custom mRNA cancer vaccine.

A month later, the tumors shrank by half.

And this is just the start of AI medicine.

[Matt Stockton @mstockton]

By far my biggest advice to anyone trying to adopt AI properly:

1. Pay a little bit of money to Anthropic
2. Download Claude Code
3. Open Claude Code
4. Press 'Shift-Tab' until it says 'plan mode on'
5. Open Voice Memo on your iPhone. Just talk about all the things you want to accomplish. When you think you are done, just keep talking. Make sure it is at least 10 minutes, hopefully longer
6. Send this Voice Memo to your computer
7. Download MacWhisper and use it to transcribe this voice memo. Trust me, you will want MacWhisper and will use it later a lot
8. Type into Claude Code: "I have never used you before but I talked about some things. I will paste those things in below. Please read the things and ask me any questions you need to in order to help me figure out how to use you to be awesome. Ask me lots of questions until I tell you I am done"
9. Then paste in the transcript
10. Then press enter

Then just let Claude take the wheel, and them please send me a DM if this works.

Also, if this just sounds crazy, just literally take this entire message and paste it into whatever AI you are using and say 'some weird person told me to paste this into you, I want to use it, but I don't know how. What should I do?'

I am just trying to help you get started. Curiosity and persistence are the most important things.

[Growth Labs @growthhub_]

She literally explained the things that therapists can't..

[Sahil @ExtraTimeMeme]

You’re bored because you’re not doing side quests, man.

Life is more than just working and then throwing yourself into bed doing nothing.

Here are 50 side quests to complete:

[TraderSZ @trader1sz]

Stop what you are doing and watch this