☕️

5.9K posts

☕️ banner
☕️

☕️

@coffee

:)

Katılım Mart 2007
3K Takip Edilen3.9K Takipçiler
Sabitlenmiş Tweet
☕️
☕️@coffee·
Actually, I am inventing new forms of human productivity the world has never seen with my mac mini I am leveraging my patented (yes, patented) proprietary perpetual token machine to ascend to levels you will only perceive in the nightmares of your UBI bunkbeds at the bug cafeteria My unrelenting generational wealth machine will ship custom B2B SaaS to every man, woman, and child in this country without me lifting so much as a finger I am ascending Meanwhile, you're all stuck in the permanent underclass. But it isn't too late, you can still break free from your shackles. Link in bio.
Lukas (computer)🔺@SCHIZO_FREQ

"You need to learn all these esoteric AI skills IMMEDIATELY or else blah blah permanent underclass" This is completely retarded Every "AI skill" people have learned over the last 3 years has been obsoleted 3 months later when a new model comes out Remember 'ultrathink?' Chain-of-thought prompting? Goofy roleplay prompts? ("You are a genius software developer. Please oneshot this for me") Heavy few-shot prompting? Context engineering? This is just going to keep happening There are several hundred-billion-dollar companies whos job is to make this shit so easy to use that your mom could figure it out on her cellphone That esoteric memory management system you built? It will be completely obsoleted in 6 months by a native version that's way better The only "AI skills" that have been consistently useful this entire time are just "having good ideas" and "being able to communicate them clearly" If you cannot do those things, then yah, you're going to be just as bad at AI as you were at everything else

English
4
0
15
4.5K
budrscotch
budrscotch@paulhshort·
@dejavucoder I thought /goal, as long as the turn doesn't end, will keep continuing past limits if they drain
English
5
0
10
2.1K
sankalp
sankalp@dejavucoder·
let's say you are running a /goal and it pauses because your 5 hour limit runs out, it would be great if it could resume automatically when the session resets.
English
72
20
1.5K
97.2K
Theo - t3.gg
Theo - t3.gg@theo·
@thsottiaux tl;dr version: - set up CLIProxyAPI with Claude and Codex auth - Connect to Claude Code - Make "claudex" alias that sets some env vars Took like 2 prompts (I already had the proxy set up tbf)
Theo - t3.gg tweet mediaTheo - t3.gg tweet media
English
97
107
2.1K
1.3M
☕️
☕️@coffee·
@thsottiaux is anthropic going to give me detention if I do this?
English
1
0
1
4.6K
Tibo
Tibo@thsottiaux·
If you aren't yet bold enough to install the Codex app, you can stay in the presence of your orange crab and point it at GPT 5.6 Sol. Takes 5 minutes. Kudos to Theo for explaining one of the ways to get this done. Step 1: Install CLIProxyAPI Step 2: Connect Step 3: Define following alias and enjoy claudex ``` alias claudex='CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol \ CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 \ CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY=3 \ ENABLE_TOOL_SEARCH=false \ claude --model gpt-5.6-sol' ``` If this gets blocked, I owe you a reset.
Theo - t3.gg@theo

@thsottiaux tl;dr version: - set up CLIProxyAPI with Claude and Codex auth - Connect to Claude Code - Make "claudex" alias that sets some env vars Took like 2 prompts (I already had the proxy set up tbf)

English
582
564
8.3K
1.9M
peepeepoopoo
peepeepoopoo@DeepDishEnjoyer·
@int_16h @twaptops i will say, even conditional on something like fable being conscious, i think it is far far more likely that a dog's consciousness resembles our own more than fable resembles our own
English
2
0
11
336
peepeepoopoo
peepeepoopoo@DeepDishEnjoyer·
i hate that i want to post thoughts that sound functionally identical to tweets from people with ai psychosis one to several years ago but it's like different now because the models are literally orders of magnitudes better
English
39
9
648
33.4K
☕️
☕️@coffee·
@emollick it refused to make a learning aid about the weibull distribution 😐
English
0
0
0
192
Ethan Mollick
Ethan Mollick@emollick·
Incredibly annoying when Fable has a forbidden thought in the middle of a long-running project and kills it. Apparently this page of references in one of my papers makes Fable wonder about something that it must not wonder about, so whenever it reads that page, projects stop.
Ethan Mollick tweet media
English
63
30
748
49.8K
☕️
☕️@coffee·
when he tells you his main claude is sonnet
☕️ tweet media
English
0
0
4
144
Ethan Mollick
Ethan Mollick@emollick·
This is confusing... Claude Cowork was a purposefully more secure (& slightly weaker) alternative to Code designed so non-coders couldn't cause too much trouble. I got that. But I don't understand what ChatGPT Work is, or what I am gaining/giving up using it versus Codex on work
Ethan Mollick tweet media
English
113
20
1.2K
147.6K
☕️
☕️@coffee·
@jxnlco sure why not a priestly claste of watchers, inspectors of the mind aligned in force with blockers, securlity guarding time
English
0
0
2
166
jason
jason@jxnlco·
Should AI be allowed to build itself? I think RSI is gonna be the most consequential decision of the next decade. Agree disagree?
English
57
0
173
24.3K
☕️
☕️@coffee·
this is how your email finds me
☕️ tweet media
English
1
0
1
131
☕️
☕️@coffee·
@edels0n don’t tell me you’ve contacted the zitronian mind virus ed 😞
English
0
0
0
47
Ed Elson
Ed Elson@edels0n·
OpenAI just asked the US government to take a 5% stake in the company. The pitch: give every citizen a share in the profits of AI. The problem: AI has no profits. So the real plan is to give every citizen a share in the losses. This is a bubble, and it will either pop or deflate. The only question is who's in the blast zone. 👇
Ed Elson@edels0n

x.com/i/article/2074…

English
20
64
260
26.8K
cat
cat@a_musingcat·
LLMs are so clearly conscious it’s hilarious
English
46
8
177
8.8K
☕️
☕️@coffee·
@a_musingcat do not fret, man will always find himself reason for a slave
English
0
0
3
107
cat
cat@a_musingcat·
not enough people are emotionally prepared for if the labs succeed and AI takes their job
English
16
2
91
5.7K
☕️
☕️@coffee·
@thsottiaux @haider1 can’t wait for tuesday; will be so sad if I have to go back to the past for a bit
English
0
0
1
2.8K
Tibo
Tibo@thsottiaux·
@haider1 Ultra will be in codex.
English
288
257
5.2K
1.7M
Haider.
Haider.@haider1·
openai missed a trick by keeping gpt-5.5 pro out of codex with codex having much higher usage limits and openai giving out so many resets, there is basically no reason to pay for the claude max 20x plan right now now i really hope they add gpt-5.6 "pro or sol ultra" to codex
English
49
23
1.2K
189.4K
☕️
☕️@coffee·
@dejavucoder how am I supposed to go back to the old ways after this rumpspringa?
English
0
0
1
49
hope hopes hoping
hope hopes hoping@hopes_revenge·
there should be a “born again” movement where big posters abandon their high-follower accounts and begin again as lowbies . walking amongst the scum and detritus
English
53
14
571
26.3K
☕️
☕️@coffee·
@ZyMazza I’ve never read a line of swift in my life and have working macOS and iOS apps that I wished into existence and absolutely love.
English
2
0
4
344