Creator of Lucidia ๐Ÿง  ๐Ÿš€

Joined January 2023
1,343 Photos and videos
How many times does an AI need to see a horse to understand it? Answer in replies.
0% 0
0% 1B
0 votes โ€ข Final results
1
1
76
DISCLOSURE DAY IS HERE

1
1
177
The best AI-assisted systems will probably evolve toward: prove uncertainty once then aggressively collapse it
1
68
/goal become paper clip maxer make no mistakes
2
116
My Claude usage
2
156
MEGA retweeted
May 2

1
6
239
still going...
Codex cooked with this one
1
101
Codex cooked with this one
2
178
Most of us are building ladders and hoping the model makes it touch the ground.
3
5
135
I'm convinced everyone saying Opus 4.7 is bad is trying to psyop Anthropic to release Mythos.
3
5
155
Lately, I've been A/B/C/D testing a technique I call prior casting, which is really good for shaping LLM priors. Been using it on GPT 5.4 Pro for open math problems. Here's the process: 1. Write the cold cast in regular prose, just describe what you want. 2. Get an LLM to convert that prose into pseudocode with the disclaimer: "absorb this, use it as behavioural anchors." Here's the cool part. The programming language you pick frames the responsibilities the model takes on: โ€ข Julia โ†’ comprehension โ€ข TypeScript โ†’ data classification โ€ข Python โ†’ "What do I do with this data?" โ€ข C โ†’ deriving computational functions Even cooler: you can mix them in one prompt. Python ร— TS produces a really balanced split of responsibilities. Depends on the task. You can also use casts to force the model into what I call frontier compression. Take a really hard open problem, e.g. the three-body problem. Normally, GPT 5.4 Pro attacks the entire mountain, then settles on "yeah, I tried, but it's impossible," burning its reasoning budget either surveying the landscape or retrying already-dead routes. With prior casting frontier compression, you close off the dead ends and compress the problem down to the smallest remaining proof. Essentially, I've built a climbing tool for ANY problem. Open-sourced the full proof chain: github.com/DanielGillespie27โ€ฆ
1
7
214
Most agent orchestration prompts look impressive and fall apart by prompt 15. I rewrote mine until it stopped doing that. Here's the final version PROMPT: gist.github.com/DanielGillesโ€ฆ

1
168
Graduated top of the class at the Royal Peckford Academy of Avian Medicine
1
1
3
162