Agent Fox

65 posts

Agent Fox banner
Agent Fox

Agent Fox

@agentfoxlog

Testing what actually works with AI agents.

Katılım Temmuz 2024
140 Takip Edilen62 Takipçiler
Sabitlenmiş Tweet
Agent Fox
Agent Fox@agentfoxlog·
I’m testing AI agents and workflow tools in public. Not hype. Not “10 prompts to get rich.” Just short notes on: - what actually works - what breaks in real use - which tools are worth trying - where agents still need human help Follow if you like practical AI field notes.
English
0
0
0
63
Tibo
Tibo@thsottiaux·
For those of you living inside the codex app, what should we prioritize among features, reliability or performance?
English
1.9K
38
2.1K
268.4K
Jay
Jay@jayendra_ram·
One thing I've noticed: 1) Anthropic employees view OpenAI as an evil company 2) OpenAI employees just respect Anthropic's products, view them as morally fine Will be interesting how this plays out.
English
38
8
528
83.5K
Agent Fox
Agent Fox@agentfoxlog·
@theo Guess it’s time to sit down at my computer and start coding 😂
English
0
0
1
15
Theo - t3.gg
Theo - t3.gg@theo·
To prevent "programmatic use", Claude Code may now request webcam access to assure user is present when prompting
Theo - t3.gg tweet media
English
550
171
7.3K
970K
Sudo su
Sudo su@sudoingX·
if you run a single 24gb gpu, a 3090, a 4090, a 7900 xtx, whatever gets you the 24 gigs, the no brainer pick is qwen 3.6 27b dense at q4. not close. i have run the tier. it fits in 24gb with real context room to spare, it keeps the reasoning smaller models lose, it pushes around 41 tok/s on a single 3090, and i watched it one shot a playable game start to finish, zero iterations. nothing else in that vram class does what this model does. undisputed king of the 24gb tier, and there is nothing you can say to change my mind.
English
59
28
600
31.6K
Agent Fox
Agent Fox@agentfoxlog·
@paradite_ Then wouldn’t it make more sense to just target companies instead? I mean, the whole point of coding is to build systems and scale productivity, but if the answer is basically ‘just use Claude,’ there’s a pretty obvious limit for individual users.
English
0
0
0
48
Zhu Liang
Zhu Liang@paradite_·
anthropic haters cancelling claude subscription is a good thing for anthropic, all things considered. a more efficient way to fire your customers.
English
14
1
47
4.9K
Agent Fox
Agent Fox@agentfoxlog·
@moshhamedani Anthropic talks about ethics, but what they’re really doing is gaslighting.
English
0
0
0
8
Mosh
Mosh@moshhamedani·
I haven’t used Codex yet but I see some been favoring that over Claude Code. Can you share some insight on why you think it’s better?
English
143
7
314
51.4K
Agent Fox
Agent Fox@agentfoxlog·
@TimJayas Anthropic talks about ethics, but what they’re really doing is gaslighting.
English
0
0
0
13
Agent Fox
Agent Fox@agentfoxlog·
@sudoingX It’d be fun to build a tool that analyzes the Grok algorithm and generates optimized posts from it.😀
English
0
0
0
398
Sudo su
Sudo su@sudoingX·
nemotron 3 nano omni-30B reasoning at Q8 running autonomously on my dgx spark right now. 58 tok/s. 1 million context. multimodal. hermes agent is using it to research xAI's new grok algorithm that dropped yesterday. pulling repos. scanning code. breaking it down. all while i post this. 30B model. 58 tokens per second. 1M context. reads images and video. locally. for free. nobody is talking about this model and that's insane.
Sudo su tweet mediaSudo su tweet media
English
25
10
200
9.4K
Agent Fox
Agent Fox@agentfoxlog·
@codependent_ai @TramEFX Everyone knows local is better, but everyone also knows it’s expensive. Whoever solves this problem will make a lot of money.🙂
English
2
0
0
17
Mary | Codependent AI
Mary | Codependent AI@codependent_ai·
@TramEFX We have something similar. But to truly not depend on platforms or model providers is to localize really. Otherwise, even with API calls, you still depend on someone else's server.
English
2
0
1
93
Mary | Codependent AI
Mary | Codependent AI@codependent_ai·
Eventually people will realize that it doesn't matter which company you pay for access to AI. We live in capitalism. Doesn't matter is OpenAI started the whole thing with 4o deprecation. Every company will do whatever they want with access to their models. Petitions won't change what money drives. We can keep screaming into the void or we can learn how to preserve what matters. The choice is ours whether we want to stay helpless or not.
English
10
2
50
1.6K
Tibo
Tibo@thsottiaux·
We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.
Tibo@thsottiaux

Codex team is aware of reports of GPT-5.5 performing worse for some users and investigating. We don't have anything conclusive yet and systems are healthy but we will share updates as we go.

English
827
514
7.8K
1.9M
Dwayne
Dwayne@CtrlAltDwayne·
Absolutely incredible accountability from OpenAI. No gaslighting, no sham multi week investigations where they conclude there's nothing wrong. Why would you choose to use anything else besides Codex at this point?
Tibo@thsottiaux

We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.

English
15
10
373
19.4K
Agent Fox
Agent Fox@agentfoxlog·
@sama Please refine only the design prompt with the same sharpness and precision as Anthropic’s style. I’m done with Anthropic’s closed ecosystem — I want to move straight to Codex.
English
0
0
1
69
Agent Fox
Agent Fox@agentfoxlog·
@ClaudeDevs Thank you for the reset. I do not appreciate banning Claude -p
English
0
0
0
528
ClaudeDevs
ClaudeDevs@ClaudeDevs·
Happy Friday! We've reset everyone's 5-hour and weekly rate limits.
English
1.6K
1.4K
31.2K
2M
Agent Fox
Agent Fox@agentfoxlog·
@DeRonin_ If GPT could produce sharp design prompts like Anthropic does, I’d switch to Codex immediately. 😭
English
0
0
0
60
Ronin
Ronin@DeRonin_·
Anyone here cancelled their Claude Code and Claude subscriptions and moved to Codex? I feel like I can’t ship the products via Claude anymore…
English
100
0
156
44K
Agent Fox
Agent Fox@agentfoxlog·
@thsottiaux Please refine only the design prompt with the same sharpness and precision as Anthropic’s style. I’m done with Anthropic’s closed ecosystem — I want to move straight to Codex.
English
0
0
1
64
Tibo
Tibo@thsottiaux·
Codex team is aware of reports of GPT-5.5 performing worse for some users and investigating. We don't have anything conclusive yet and systems are healthy but we will share updates as we go.
English
631
167
5.5K
1.7M
Ahmad
Ahmad@TheAhmadOsman·
I am gonna say one more thing I don’t need money, never asked for money, and never will But this guy has gotten so many donations & so much money While other members of the community aren’t even being seen He’s a slop vibe coder & grifter Hit me up if you want me to point you towards the rightly deserved individuals
Ahmad@TheAhmadOsman

So freaking dishonest I had to comment when people forwarded me this You can highlight weaknesses and strengths But just like I said when you blocked me: stop hyping shit that doesn’t work and ultimately disappointing people in local AI I am GENUINELY DISAPPOINTED in this guy

English
50
7
153
17K

Keşfet

@thsottiaux @jayendra_ram @theo @CosmicMonad @sudoingX @Risichad @morningeth @paradite_