Ludwig 🦊

796 posts

Ludwig 🦊

Ludwig 🦊

@LudwigTrades

Why are you following a fox?

Katılım Haziran 2020
917 Takip Edilen49 Takipçiler
Bindu Reddy
Bindu Reddy@bindureddy·
Running loops burning infinite tokens a day leads to extreme brain rot Once AI has generated 10k lines of code, engineers have zero idea of what is going on The bugs multiply, AI debt spins out of control and uptime drops
English
41
5
140
7.9K
Zibo Gao
Zibo Gao@gao_zibo·
codex mac app is winning SO HARD. just need: - native editor - iOS app - full browser - openclaw then it might be the home default app
English
44
23
1.6K
127K
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
hey @thsottiaux if you want to hit that reset codex limit button, now would be a great time... Just saying
Ludwig 🦊 tweet media
English
0
0
1
61
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
Claude back to being SUPER dumb today
English
0
0
0
14
Sam Altman
Sam Altman@sama·
wow y'all love 5.5 we should think of something nice to do to celebrate!
English
2.6K
285
11.1K
780K
Free_Willy
Free_Willy@dcbuilds_right·
@sdrzn Deepseek is more or less free
English
1
0
1
177
Saoud Rizwan
Saoud Rizwan@sdrzn·
last week anthropic removed claude code from their pro plan yesterday github copilot switched to usage based billing, 6x multiplier for gpt and 27x for opus... as soon as openai goes public i won't be surprised if the codex reset button breaks the era of free tokens is ending.
Saoud Rizwan tweet mediaSaoud Rizwan tweet media
English
16
4
90
12.3K
Tibo
Tibo@thsottiaux·
Don't just reset Codex rate limits for fun, it costs money. Don't just reset Codex rate limits for fun, it costs money. ... but the vibes are good ... I have reset Codex rate limits for ALL paid plans to celebrate a good week and allow everyone to build more with GPT-5.5. Enjoy
English
1.5K
764
17.2K
1.3M
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
@Teknium @NousResearch Real question, how do you keep up with context switching? My brain feels fried after a few hours switching between 6 agents running
English
1
0
1
175
Teknium 🪽
Teknium 🪽@Teknium·
I literally run 12 hermes agent instances every day in parallel to build Hermes Agent, and its now a top 100 GitHub repositories of all time. Agents do bring value and do create substantive software and work.
David Cramer@zeeg

Everyone is slowly coming to this realization, and I assure you, no one is running multitudes of agents overnight. No one that is doing anything of substance at least. There _are_ people pretending to be scientists, or fully caught up in their drug infused AI overdose, that think their slop machines are changing the world. They're not tho, and they're just wasting a bunch of money and compute to create a lot of LoC that will just get thrown away. The state of the art is still "can we even one shot a production quality patch that we wont regret later", and its rarer than you'd expect based on discourse.

English
149
113
2K
180.7K
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
@Teknium Another interesting concept I have is /trip Simulates a dmt trip for the agent, forces to lower the rational barriers and allow unusual connections
English
0
0
1
19
Teknium 🪽
Teknium 🪽@Teknium·
What features, capabilities or ideas do you have for Hermes Agent that would unlock your ideas for submissions to the Hermes Agent Creativity Hackathon?
English
103
10
235
17.2K
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
@Teknium I have been running two concepts that I find interesting. One reading session and one dreaming session each night. The agent is free to read on any subject to gain more knowledge then the dreaming session is about connecting the dots, what did it read that can apply to real issue
English
0
0
1
37
Craig Weiss
Craig Weiss@craigzLiszt·
prediction: codex will take the lead over claude by end of year
English
156
31
1K
56.6K
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
well it looks like GPT-5.5 is limited to a 272K context, unusable on large codebases.
Ludwig 🦊 tweet media
English
0
0
0
30
min heo
min heo@minheo93698092·
When I use the GPT-5.5 model in Hermes Agent, I get this error message. Is this happening to anyone else? The context length will be reduced from 1,050,000 to 128,000 tokens. @Teknium
min heo tweet media
English
2
0
9
2.7K
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
@gaogezh @Teknium @minheo93698092 @Teknium 📷 Elapsed: 1.66s Context: 158 msgs, ~272,313 tokens 📷 Context length exceeded — stepping down: 1,050,000 → 128,000 tokens 📷 Context too large (~272,313 tokens) — compressing (1/3)...
English
0
0
0
13
Ludwig 🦊
Ludwig 🦊@LudwigTrades·
@gaogezh @Teknium @minheo93698092 I see 258k in codex app on macOs. And this poped up in hermes "[subagent-0] 📷 Compression model (gpt-5.5) context is 272,000 tokens, but the main model's compression threshold was 892,500 tokens. Auto-lowered this session's threshold to 272,000 tokens so compression can run."
English
1
0
1
119

Keşfet

@0xSunRun @bindureddy @vultuk @thsottiaux @sama @gao_zibo @NousResearch @dcbuilds_right