Logo
Picture

Centipede5 @Centipede5dev

Rutgers CS - web game dev of 5M+ Players - Currently Agent Puppeteer autogamestudio.ai New Jersey Joined April 2018
  • Tweets
    134
  • Followers
    335
  • Following
    175
  • Likes
    297
Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 days ago

Lazy modeling choice. As you can see their model predicts that people with a super high IQ will start to have a lower SAT score vs someone with a moderately high IQ - obviously ridiculous. Not to mention if you extrapolate this outside their range you end up with impossible/ subzero scores on either end. SAT scores are not just a number, they are essentially N bernoulli trials with some latent skill's influence. Using polynomial regression completely ignores the structure of the problem and pretends this is just some random numerical data. Note, that's not to say that a more reasonable model would lead to a different conclusion.

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

a week ago

I don't buy this at all, even in this paradigm, agents still would need to rely on high quality libraries/services (as they do currently). Even if AI has a large hand in writing those libraries the concept of re-usable code creates the need for software engineering somewhere in the pipeline.

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 weeks ago

Well played @sama, I got way too used to burning through 5.5 xhigh fast mode on the 10x codex promotion and now I'm gonna have to upgrade to pro

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 weeks ago

@systematicls Wait until you hear about EV depending on the utility function

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

a month ago

@raw_works How much of the improvement for the explicit problems actually comes from code execution as a reasoning substrate vs the recursive subagents doing an Atom-of-Thought-like decomposition? How many of the traces actually contain code doing heavy lifting beyond just calling agents?

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

a month ago

@simpsoka Constant cybersecurity warnings suddenly for frontend work / data science.

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

a month ago

Also somehow it completely stopped late at night when usage probably drops...

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

a month ago

The whole "flagged for possible cybersecurity risk" is bullshit right? They just don't have enough compute to serve 5.5 for the exploding number of codex users. I've been getting this every few hours for the most benign SWE work ever.

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

a month ago

3d spatial reasoning is probably the weakest technical link. Ive tried all frontier models but they almost always struggle to correctly scale/ rotate assets in 3d. Not too big of a deal for me to do manually but annoying that it breaks the loop for a non-taste reason. I have a few scripts that work ~80% of the time but definitely not solved

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

This is kind of a meaningless metric if you think about it. Addition of a 1 digit number takes a person maybe a second, a 4 digit number 4 seconds etc. You could make the exact same graph with the task of addition and show how there was an "intelligence explosion" in the 1940s. If you use AI regularly you know that long context tasks are not really the bottleneck anymore outside of maybe frontier math. Jagged intelligence

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

Autogamestudio has been absolutely insane after gpt-image-2 dropped, custom sprite animations are finally feasible

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

3 months ago

I took @karpathy’s autoresearch loop and applied it to game development, here's what it built last night: Agents read player data → plan improvements → spin up new git branches in a game evolution tree → ship playable HTML5 variants → repeat forever. The system optimizes

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

@Alibaba_Qwen @arena Embarrassing

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

@mdancho84 Why does this shit keep getting posted every single time a new model comes out???

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

Surrogate models are going to be the next big thing in LLM harness development

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

@thomasfbloom Human mathematicians won't scale with Moore's law though

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

Interesting read. I imagine true in-context learning will appear when the memory systems themselves are more integrated into training beyond just learning tool calls, maybe some kind of recurrent attention model. Bitter lesson will eventually come for all of the engineering hacks currently deployed.

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

@alexandr_wang Wow, new SOTA in bioweapons refusal! Never doubt meta superintelligence

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

@joelniklaus Very interesting read! Have you experimented at all with prompt optimization techniques such as GEPA?

Centipede5dev Profile Picture

Centipede5 @Centipede5dev

2 months ago

@cloneofsimo Thank you for this, the original 2d "donut" chart is extremely misleading

Trends for United States

Ghana
#AEWDynamite
Croatia
Rashford
Harry Kane
Versailles
Yasmine
Ronaldo
Boyle Heights
Portugal
laila edwards
Geraldo
Charleston, IL
Kenny Omega
Gordon
San Jose
Ayew
#ENGCRO
Rodon
SEND THEM BACK

You might like

#crypto#forex#backtocrypto
Hooli
@20xHooligan
4K Followers
Leforyah
@leforyah
172 Followers
🎧 ❣️
Bren Rodmo
@brenrodm
61 Followers
If you find yourself in a fair fight, you didn’t plan your mission properly
Afzal Chohan
@AfzalTotal
52 Followers
RGCET ian😉 Puducherry ian😁
Pradhap kp
@PradhapJanarth
623 Followers