this post was submitted on 26 Oct 2025
776 points (96.3% liked)

World News

50583 readers
2331 users here now

A community for discussing events around the World

Rules:

Similarly, if you see posts along these lines, do not engage. Report them, block them, and live a happier life than they do. We see too many slapfights that boil down to "Mom! He's bugging me!" and "I'm not touching you!" Going forward, slapfights will result in removed comments and temp bans to cool off.

We ask that the users report any comment or post that violate the rules, to use critical thinking when reading, posting or commenting. Users that post off-topic spam, advocate violence, have multiple comments or posts removed, weaponize reports or violate the code of conduct will be banned.

All posts and comments will be reviewed on a case-by-case basis. This means that some content that violates the rules may be allowed, while other content that does not violate the rules may be removed. The moderators retain the right to remove any content and ban users.


Lemmy World Partners

News !news@lemmy.world

Politics !politics@lemmy.world

World Politics !globalpolitics@lemmy.world


Recommendations

For Firefox users, there is media bias / propaganda / fact check plugin.

https://addons.mozilla.org/en-US/firefox/addon/media-bias-fact-check/

founded 2 years ago
MODERATORS
 

President Donald Trump was once again fact-checked following an embarrassing tantrum over a Canadian advertisement.

The ad quoted former U.S. President Ronald Reagan from 38 years ago criticizing tariffs -- a policy tool Trump frequently employs. The commercial includes audio clips from an April 25, 1987 radio address where Reagan stated: "Over the long run such trade barriers hurt every American worker and consumer.''

you are viewing a single comment's thread
view the rest of the comments
[–] 1985MustangCobra@lemmy.ca 13 points 4 days ago (3 children)

yes we used AI from the 80s. We pulled out a lisp machine.

[–] humorlessrepost@lemmy.world 6 points 4 days ago* (last edited 4 days ago)

B:\> ren eliza.bas reagan.bas

[–] WhiskyTangoFoxtrot@lemmy.world 3 points 4 days ago* (last edited 4 days ago)

Shall we play a game?

[–] ms_lane@lemmy.world 1 points 4 days ago

From chatgpt-

Prompt: What is a very rough ballpark figure of how long it would take a Symbolics 3600 to process this request on you?

That’s a fascinating question — and quite a big gap in computing history!

Let’s estimate very roughly:

  1. Symbolics 3600 performance

Released around 1983.

Based on a 10 MHz 68000-series CPU with extensive microcode for Lisp operations.

Effective performance: roughly 1 MIPS (1 million instructions per second), though Lisp code was often slower due to dynamic typing and garbage collection.

Floating-point and memory bandwidth were also very limited — on the order of kilobytes per microsecond.

  1. This request

Let’s say your request (this chat exchange) takes me — a large language model with billions of parameters — maybe a few hundred billion floating-point operations (FLOPs) to process. For perspective, a modern GPU (like an NVIDIA A100) can do around 10¹⁵ FLOPs per second (1 petaFLOP) for AI workloads.

  1. Comparison

If we very loosely assume:

Symbolics 3600: ~1 MFLOP (10⁶ FLOPs/sec, being generous)

Modern GPU: ~10¹⁵ FLOPs/sec

That’s a factor of 10⁹ difference.

So if a modern GPU takes about 0.1 s to process your request, then the Symbolics 3600 would take:

0.1 s × 10⁹ = 10⁸ s ≈ 3 years

And that’s if it could even hold the model in memory, which it couldn’t — it had only a few megabytes of RAM, versus the hundreds of gigabytes (or terabytes) needed.