Justin Smith

AI researcher mapping human–LLM capability boundaries. Building validation systems and games to explore how humans and AI interact.

[Justin Smith @Aihumanbench]

my website is done!😄👇
You are welcome to make suggestions.
https://t.co/IVfo9gUzNI

[Justin Smith @Aihumanbench]

@AdeTheGangster go to https://t.co/IVfo9gUzNI

[Justin Smith @Aihumanbench]

⚡ How fast are you?
400+ ms: Refocus & retry
300–400 ms: Beginner
200–300 ms: Average
150–200 ms: Pro Gamer
120–150 ms: Elite
Under 100 ms: Superhuman? Probably a false start or prediction.
Test your 5-round average:
https://t.co/wToa88yRg0
#ReactionTime #Gaming https://t.co/nIYw8uHti6

[Justin Smith @Aihumanbench]

@AskPentasuJP ok!

[Justin Smith @Aihumanbench]

If human brain's long-term memory is ~2.5 PB:
• HDD: ~$60K
• Enterprise NVMe: ~$350K
• DDR5 ECC RAM: ~$80-100M
Storing 2.5 PB is cheap. Making it instant, associative, & computational is astronomical.
Good news: Your brain just appreciated in value.😀

[Justin Smith @Aihumanbench]

@122362FU 😁

[Justin Smith @Aihumanbench]

AI can already perform an enormous amount of computation.
But more compute doesn’t automatically mean better judgment.
Humans still have an important advantage in many real-world situations: knowing when something looks wrong, ambiguous, or uncertain.

[Justin Smith @Aihumanbench]

Ever wondered how your brain stacks up against AI? 🧠⚡
Test your reaction speed, memory, logic, and problem-solving skills
Ready to find out? 👉 https://t.co/IVfo9gUzNI
#AI #HumanVsAI #BrainTest #AIHumanBench

[Justin Smith @Aihumanbench]

For more useful comparisons:

1. Repeat the same test under similar conditions.
2. Compare your median—not your best attempt.
3. Track each memory type separately.

A spatial-memory score shouldn’t be treated as interchangeable with working memory.

[Justin Smith @Aihumanbench]

Memory isn’t one ability.

Different tests can measure very different things:
• Short-term: brief retention
• Working: hold + manipulate
• Spatial: locations + relationships
• Auditory: sound patterns

A low score in one task doesn’t mean you have a “bad memory.” #AI #Agent

[Justin Smith @Aihumanbench]

Your reaction-time score isn’t just reflexes.

Four things can change it:
• Sleep and vigilance
• Focus and distractions
• Practice and anticipation
• Display and input latency

For a fairer comparison: use the same device, run 5 attempts, and compare the median—not your best score.

[Justin Smith @Aihumanbench]

Explore the project and take the first benchmark:
https://t.co/YWCpMmoYjR

Which human ability should we test first?

[Justin Smith @Aihumanbench]

Where do humans still outperform AI?
The answer changes with every model release.

AIHumanBench is mapping that boundary across reaction, memory, logic, creativity, and social reasoning.
We’ll publish the tests, results, and limitations—not just the conclusions.

[NVIDIA @nvidia]

The first CPU built for agents is going to work at scale.

@SpaceX is deploying NVIDIA Vera to accelerate the orchestration, code execution, and data processing that powers its next generation of agentic AI — keeping GPUs fed and agents acting fast.

From gigawatt AI factories to orbit. One NVIDIA architecture, everywhere.

[Justin Smith @Aihumanbench]

Nice to see modularity pushed this far — even the agent loop, sessions, storage, and UI are swappable. Curious to see how well it holds up in real-world use.👏

[DeepSeek @deepseek_ai]

🧩 DeepSeek Harness v0.1 is now available in Developer Preview!

🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license.
🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one core idea: Everything is a plugin. Models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and UI are ALL implemented as plugins, and can be mixed, matched, replaced, and extended.

Try it now!
https://t.co/2YWSvJHhKA

[Justin Smith @Aihumanbench]

@mitsuhiko How much of “agent intelligence” is actually model capability, and how much is harness engineering?

[Justin Smith @Aihumanbench]

Just tried it—seriously impressive.

[Black Forest Labs @bfl_ai]

FLUX 3 Video is #2 in the world.

To celebrate, FLUX 3 Video is free to use in our playground until Sunday 16th, 11:59pm PT (link in the thread).

This is just the beginning of what’s coming. Up next: 4K, video editing, and multiple images & videos as reference input.

[Justin Smith @Aihumanbench]

@bfl_ai Just tried it—seriously impressive.

[Justin Smith @Aihumanbench]

@aijoey @herdrdev @NVIDIAAI @TermiusHQ interesting!