modifylife

143 posts

modifylife

modifylife

@FallisAaro51194

Katılım Kasım 2024
198 Takip Edilen3 Takipçiler
REAL BANNED PEPE
REAL BANNED PEPE@RealBANNED_PEPE·
@adcock_brett You know if you made the machine not look like a human it would do a better job? This creepy obsession with trying to replace humans is deeply evil and sick and we dont have to do it
English
7
0
25
7.3K
Brett Adcock
Brett Adcock@adcock_brett·
We just wrapped what began as an 8-hour challenge - and it ran for 200 hours without a failure Shoutout to the team for the hardcore engineering behind F.03 and the robust Helix models powering it
English
826
1.2K
10.4K
4.8M
modifylife
modifylife@FallisAaro51194·
@rezoundous I tthink corporate burcocy is getting in the way and there scared to ship an actual product there acting like it's an app that only slightly changes in a year while every one else ships weekly
English
0
0
0
755
Tyler
Tyler@rezoundous·
Google's fumble with Gemini and Antigravity needs to be studied.
English
59
20
755
66.4K
modifylife
modifylife@FallisAaro51194·
@adcock_brett Now tackle hunger and housing have it grow food and give it away for free and build houses
English
0
0
0
9
modifylife
modifylife@FallisAaro51194·
@mark_k All plus opensource depending on the project
English
0
0
0
5
Mark Kretschmann
Mark Kretschmann@mark_k·
Ok, vibe coding poll time: Which agentic AI coding tool are you using right now? (If your tool isn't listed, please answer in a comment!)
English
53
5
43
20.7K
modifylife
modifylife@FallisAaro51194·
@adcock_brett Fun to watch while I build my hermes agent a robot body using skr pro steper motors and a pi5. Well hermes did the coding i just wired
modifylife tweet media
English
0
0
0
552
modifylife
modifylife@FallisAaro51194·
@Figure_robot 1 figure robot if charged while working can work for 8760 hours a year where one human works 1920 hours a year that's 1 figure for every 4.56 humans 🤔
English
1
0
0
2.2K
Figure
Figure@Figure_robot·
We're now on Day 4 of nonstop autonomous operations with F.03 humanoid robots running 24/7 until failure x.com/i/broadcasts/1…
English
321
733
4.3K
1.5M
Brett Adcock
Brett Adcock@adcock_brett·
I huddled with the team. Tomorrow we’re putting a human head-to-head against the robots Let’s settle this once and for all
modifylife@FallisAaro51194

@adcock_brett Need a human doing the same job to compare

English
84
71
943
62.7K
Brett Adcock
Brett Adcock@adcock_brett·
Limited Edition Figure Livestream Merch??
English
38
5
126
21.8K
Brett Adcock
Brett Adcock@adcock_brett·
Day 2 is Live: Watch humanoid robots Bob, Frank, and Gary running 24/7. This is fully autonomous running Helix-02 x.com/i/broadcasts/1…
English
140
164
1.3K
146.1K
modifylife
modifylife@FallisAaro51194·
@Taniyatweets_ Money grab longer responses eat tokens and the model has no problem writing a book that's how anthropic wants it. CLASS ACTION?
English
0
0
0
34
Taniya
Taniya@Taniyatweets_·
Dear Anthropic, please stop treating Claude Code users like beta testers Hitting limits after a few prompts on a paid plan is getting ridiculous
Taniya tweet media
English
265
89
2.3K
267.6K
modifylife
modifylife@FallisAaro51194·
@petergyang Recursive self slop if anyone builds it everyone lives lol
English
0
0
0
126
Peter Yang
Peter Yang@petergyang·
Here's a common trap with AI if you're not careful: 1. You ask it to generate some markdown files (maybe to build some skills). You skim them and they look ok. Sure, there's a bit of slop in there, but you're too lazy to edit them manually. 2. Over time you ask it to generate more markdown files. Except now it's referencing the previous files to write the new ones. 3. What started as 5% slop becomes 10% and then more. Before you know it, you've got a pile of AI-generated slop that feels overwhelming and have no idea how any of it actually works. 🥲
English
123
18
616
94.3K
modifylife
modifylife@FallisAaro51194·
@ClaudeDevs So now instead of 15 mins of coding you can work for 30. Remove all limits and stop on boarding until you have more capacity and make claude stop writing a book with every response eating tokens like tic tacs
English
0
0
0
13
ClaudeDevs
ClaudeDevs@ClaudeDevs·
Usage limits are up, effective today we're: 1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans 2) Removing peak hours limit reduction on Claude Code for Pro and Max plans 3) Substantially raising our API rate limits for Opus models
Claude@claudeai

We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.

English
1.5K
3.2K
41.3K
3.9M
modifylife
modifylife@FallisAaro51194·
Researching converting python to emoji python a conversion of python into emoji creating a key map that maps every part of python to emoji train the model on the key then the model writes all python code in emoji and sends it to the user who uses a translator script
English
0
0
0
34
modifylife
modifylife@FallisAaro51194·
@bcherny Building emoji py converting python scripts to an emoji version give the key to the model and reduce token use 60% ai dosnt need human the fluff humans do. Still a research project but promising
English
0
0
0
126
Boris Cherny
Boris Cherny@bcherny·
It's been an amazing start to Code w/ Claude! Love hearing what people are building with Claude Code and getting feedback on what we can do better.
English
149
34
1.9K
111.3K
modifylife
modifylife@FallisAaro51194·
@petergyang A app that allows them to collect license plates by finding the state and clicking on it. Teaches geography and keeps them busy
English
0
0
0
6
Peter Yang
Peter Yang@petergyang·
I want to get my 8 year old to start building stuff with agents that she actually can share with her class and teachers. Any ideas? Maybe she can make her first dollar online too.
English
84
3
108
26.9K
modifylife
modifylife@FallisAaro51194·
@NousResearch @arcee_ai Have had some really good luck improving hermes by using vs code with copilot and sonnet 4.6 where it runs hermes and interacts and critiques it's responses then works with hermes to self improve
English
0
0
0
682
Nous Research
Nous Research@NousResearch·
Trinity-Large-Thinking, @arcee_ai's latest model, is now free on Nous Portal for the next week Sign up for Nous Portal to use it in your Hermes Agent today
English
36
40
672
225K
Sudo su
Sudo su@sudoingX·
end the debate. best agentic harness in 2026?
English
73
16
125
18.7K
modifylife
modifylife@FallisAaro51194·
@NousResearch Fitting music made me think of the opening to the shinning
English
0
0
0
154
Nous Research
Nous Research@NousResearch·
The Hermes Agent Creative Hackathon ends on Sunday, just enough time for a last minute weekend project! Here's a thread of some of the powerful creative skills and tools we've released that might help get you started:
English
24
65
707
78.1K
Romain Huet
Romain Huet@romainhuet·
Hello builders! What did you build this weekend with Codex + GPT-5.5? Drop it below, I’d love to see what you made!
English
163
10
256
29.6K