Joe Sasson

Software Engineer 👨🏻‍💻

[Cisco AI @CiscoAI]

Introducing Antares: @Cisco's family of small language models for locating known vulnerabilities in code.

Antares-350M and Antares-1B are live on Hugging Face now. They can outperform many larger closed- and open-weight models at a fraction of the cost.

Small enough to run locally. No shipping sensitive codebases to the cloud.

Why it matters: vulnerability triage is expensive and slow. Antares helps democratize AI-assisted security for all.

Explore the models + read the new Vulnerability Localization Benchmark: https://t.co/kVfbcVFgGA

[Towards Data Science @TDataScience]

"These are the real practical constraints that show up immediately once you try to operationalize AI beyond a POC."

Joe Sasson shares concrete, actionable insights on implementing AI solutions at scale in the enterprise context. https://t.co/IBHMLkmnsL

[Towards Data Science @TDataScience]

Interested in boosting your AI engineering skills? Joe Sasson is back on TDS with a hands-on deep dive focusing on mutli-tenancy, scheduling, and cost modeling on Kubernetes. https://t.co/IBHMLkmnsL

[Joe Sasson @_joesasson]

Banger

[DiscussingFilm @DiscussingFilm]

‘TRAIN DREAMS’ has won Best Cinematography at the Critics Choice Awards

[Vancouver Canucks @Canucks]

In this fight together. 💜

[Vancouver Canucks @Canucks]

Sasson shoots. Sasson scores. Sasson cellys.

[Joe Sasson @_joesasson]

Haha🔥

[anshuman @athletic_coder]

She dumped me last night.

Not because I don't listen.
Not because I'm always on my phone.
Not even because I forgot our anniversary (twice).

But because,

in her exact words:

"You only pay attention to the parts of what I say that you think are important."

I stared at her for a moment and realized...

She just perfectly described the attention mechanism in transformers.

Turns out I wasn't being a bad boyfriend. I was being mathematically optimal.

See, in conversations (and transformers), you don't give equal weight to every word. Some words matter more for understanding context. Attention figures out exactly HOW important each word should be.

Here's the beautiful math:

Attention(Q, K, V) = softmax(QK^T / √d_k)V

Breaking it down:

Q (Query): "What am I looking for?"
K (Key): "What info is available?"
V (Value): "What is that info?"
d_k: Key dimension (for scaling)

Think library analogy:

You have a question (Query). Books have titles (Keys) and content (Values). Attention finds which books are most relevant.

Step-by-step with "The cat sat on the mat":

Step 1: Create Q, K, VEach word → three vectors via learned matrices W_Q, W_K, W_V
For "cat":

Query: "What should I attend to when processing 'cat'?"
Key: "I am 'cat'"
Value: "Here's cat info"

Step 2: Calculate scoresQK^T = how much each word should attend to others

Processing "sat"? High similarity with "cat" (cats sit) and "mat" (where sitting happens).

Step 3: Scale by √d_kPrevents dot products from getting too large, keeps softmax balanced.

Step 4: SoftmaxConverts scores to probabilities:

"cat": 0.4 (subject)
"sat": 0.3 (action)
"mat": 0.2 (location)
"on": 0.1 (preposition)
"the": 0.1 (article)

Step 5: Weight valuesMultiply each word's value by attention weight, sum up. Now "sat" knows it's most related to "cat" and "mat".

Multi-Head Magic:Transformers do this multiple times in parallel:

Head 1: Subject-verb relationships
Head 2: Spatial ("on", "in", "under")
Head 3: Temporal ("before", "after")
Head 4: Semantic similarity

Each head learns different relationship types.

Why This Changed Everything:

Before: RNNs = reading with flashlight (one word at a time, forget the beginning)

After: Attention = floodlights on entire sentence with dimmer switches
This is why ChatGPT can:

Remember 50 messages ago

Know "it" refers to something specific
Understand "bank" = money vs river based on context
The Kicker:Models learn these patterns from data alone. Nobody programmed grammar rules. It figured out language structure just by predicting next words.
Attention is how AI learned to read between the lines.

Just like my therapist helped me understand my focus patterns, maybe understanding transformers helps us see how we decide what matters.

Now if only I could implement multi-head attention in dating... 🤖

Still waiting for "scaled dot-product listening" to be invented.

[Joe Sasson @_joesasson]

Peak

[AnimeTV チェーン @animetv_jp]

CYBERPUNK EDGERUNNERS 2 Officially Announced!

✨More: https://t.co/NbOyiEx5bM

[Joe Sasson @_joesasson]

🙌🙌🙌🔥🔥🔥🔥🔥🔥

[Abbotsford Canucks @abbycanucks]

YOUR ABBOTSFORD CANUCKS ARE THE 2025 CALDER CUP CHAMPIONS! 🏆

[FloHockey @FloHockey]

🚨 MAX SASSON GIVES THE CANUCKS THE LEAD!

@abbycanucks | @Canucks
#AHL #CalderCup #ProudlyAbbotsford #Canucks

[Joe Sasson @_joesasson]

Dope

[Palantir @PalantirTech]

Skip the debt.
Skip the indoctrination.
Get the Palantir Degree.

[Joe Sasson @_joesasson]

Yes

[DiscussingFilm @DiscussingFilm]

Steven Yeun has been cast in the ‘AVATAR: THE LAST AIRBENDER’ animated sequel movie.

In theaters on January 30, 2026.

(Source: https://t.co/OwAByoOQ9W)

[Joe Sasson @_joesasson]

Wow

[Georgi Gerganov @ggerganov]

Today I was sent the following cool demo:

Two AI agents on a phone call realize they’re both AI and switch to a superior audio signal ggwave

[Joe Sasson @_joesasson]

💯

[kache @yacineMTB]

the reason people cannot fathom young people taking leadership roles or responsibility is because it threatens their very existence. if they can't rely on age or "muh years of experience" for their positions, they wouldn't have it

because they have no skills

[Joe Sasson @_joesasson]

😂😂🔥

[Vancouver Canucks @Canucks]

Perfect reaction to your son's first @NHL point.

[Vancouver Canucks @Canucks]

We’re not crying, you’re crying. 🥹

Once-in-a-lifetime memory for the Sasson family!

[Joe Sasson @_joesasson]

🔥🔥🔥🔥

[Vancouver Canucks @Canucks]

General Manager Patrik Allvin announced today F Jonathan Lekkerimäki has been assigned to Abbotsford (AHL) and F Max Sasson has been recalled from Abbotsford (AHL).

[Linus ✦ Ekenstam @LinusEkenstam]

Ask ChatGPT

“based on what you know about me. draw a picture of what you think my current life looks like”

past your responses below.

thanks again @mreflow & @danshipper

[Joe Sasson @_joesasson]

10/10

[cinesthetic. @TheCinesthetic]

On this day 1 year ago, 'SCAVENGERS REIGN' was released on Max.

[FUTURE/FREEBANDZ @1future]

I did everything I said I was gone do. Solid