RG

47 posts

RG banner
RG

RG

@reasonableglyph

breaker, sometimes builder

Beigetreten Nisan 2026
23 Folgt1 Follower
RG
RG@reasonableglyph·
@melvynx I wouldn’t agree with this as it has changed a lot for me for day to day coding
English
0
0
0
401
Melvyn • Builder
Melvyn • Builder@melvynx·
Please be serious about Fable: for day to day coding, can we agree it doesn't change a lot and the hype is 10x the real value or no?
English
85
5
304
62.2K
RG
RG@reasonableglyph·
@suni_code This aged well
English
1
0
4
2.7K
Suni
Suni@suni_code·
DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS I repeat. DON'T USE FABLE 5 TO BUILD PERSONAL PROJECTS
English
444
49
2.8K
2M
RG
RG@reasonableglyph·
@anshuc Do you need to click the links or just use Claude code like normal?
English
0
0
0
119
BridgeMind
BridgeMind@bridgemindai·
Claude Fable 5 is so good that I had it build a feature in BridgeSpace that allows me to connect all of my $200 Claude Max subscriptions and switch between them in a single click. If you are a Claude power user with multiple subscriptions... this is for you. Official demo coming tomorrow.
BridgeMind tweet media
English
42
11
330
19.3K
RG
RG@reasonableglyph·
@bridgemindai Any idea if it will be able to be used on subscription plans?
English
0
0
0
246
BridgeMind
BridgeMind@bridgemindai·
Claude Mythos is about to release. It will be the best AI model in the world. It will also be the most expensive. $25/m input. $125/m output. I bought 3 $200/month Claude Max subscriptions in preparation for Mythos. The benchmarks are incredible, but there is more to a model than benchmarks. Are you ready for Claude Mythos?
BridgeMind tweet media
English
176
42
937
116.1K
RG
RG@reasonableglyph·
@0xPrajwal_ Depends what week it is
English
0
0
0
4
Prajwal
Prajwal@0xPrajwal_·
I'm a Codex user. Give me one reason to switch to Claude.
Prajwal tweet media
English
220
6
273
65.5K
RG
RG@reasonableglyph·
I used it heavily for a day when 4.8 came out to get a good feel for it, and the results were very disappointing. Some tasks were spawning 200 opus subagents and obviously it cost a ton but the problem is the code was so buggy and unusable that I had to revert almost all of it. I had SIGNIFICANTLY better results with high (not even xhigh) effort with multiple chats in worktrees
English
0
0
0
107
BridgeMind
BridgeMind@bridgemindai·
Claude Code ultracode is mostly hype for Anthropic's IPO. After using it for 10 days I can confirm that the use cases where this should be used are VERY limited. I find it hallucinating all over the place. I was running over 100 Claude Opus 4.8 agents and it caused a bunch of bugs. It feels like it puts too many cooks in the kitchen. The only thing this is one shotting is usage limits. What do you think of ultracode so far?
GIF
English
109
12
347
30.6K
RG
RG@reasonableglyph·
@OpenAIDevs @simpsoka Testing iOS apps within the app is a game changer!
English
0
0
1
2.1K
OpenAI Developers
OpenAI Developers@OpenAIDevs·
More of the iOS app loop, now inside Codex. The Build iOS Apps plugin lets Codex view and test your iOS app in the in-app browser, open SwiftUI previews, and hot reload edits without leaving Codex.
English
294
713
8.8K
1.9M
RG
RG@reasonableglyph·
@huge_icons So true 😂
English
1
0
1
42
Hugeicons
Hugeicons@huge_icons·
be honest, who relates? 🤔
Hugeicons tweet media
English
5
1
29
1.1K
RG
RG@reasonableglyph·
@thsottiaux Dreams do come true 🤩
English
0
0
0
24
Tibo
Tibo@thsottiaux·
Hi. Over the last 24 hours we had three separate small incidents that affected Codex reliability. Those are three too many and we are taking active steps for them to not reproduce. I have reset usage limits for Codex across all paid plans. May the tokens flow again.
English
1K
509
11.1K
1.2M
ClaudeDevs
ClaudeDevs@ClaudeDevs·
We've reset 5-hour and weekly rate limits for all users on Pro and Max plans. We fixed an issue that caused some Claude Code sessions to spawn excessive parallel subagents, burning through usage faster than expected.
English
1.1K
1K
20.5K
2.5M
RG
RG@reasonableglyph·
@ShishirShelke1 Half the memory bandwidth of m5 max
English
0
0
0
39
Shishir
Shishir@ShishirShelke1·
Microsoft’s MacBook Pro competitor is here: Surface Laptop Ultra - 15" Mini-LED touchscreen display - Up to 2000nits of peak HDR brightness - Large haptic touchpad - Nvidia RTX Spark (20-core ARM CPU) - Blackwell GPU (6144 CUDA Cores) - Up to 128GB unified memory - 1 petaflop of AI compute - HDMI, 3x USB-C, 1x USB-A - SD card slot | 3.5mm Jack Available this fall
English
294
141
2.8K
780.4K
RG
RG@reasonableglyph·
@simpsoka The default post-task summaries are quite noisy and overly verbose. Would love more built in customization of output
English
0
0
1
119
Kath Korevec
Kath Korevec@simpsoka·
What other Codex papercuts should we fix?
English
367
5
286
35.5K
Robin Ebers · AI for Business Owners
goodbye codex unsubscribed from the $200/mo plan for now → love the team → love the app → love the intelligence of the model but my business isn't just about backend code it's a lot of landing pages. a lot of emails. a lot of content, intros, scripts, tweets, and instagram carousels. none of which codex is good at
Robin Ebers · AI for Business Owners tweet media
English
183
4
348
88.1K
Zed
Zed@zeddotdev·
You can now use your ChatGPT subscription in the Zed agent, with the same usage and rate limits you benefit from in Codex directly. We're grateful that @openaidevs continues to support subscription-based access for third-party tools, even as others move toward usage-based billing.
Zed tweet media
English
147
220
3.8K
445.1K
RG
RG@reasonableglyph·
@thsottiaux I am not really noticing a difference thankfully. Thanks for the transparency
English
0
0
0
2.4K
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
623
164
5.5K
1.8M
alisa rae .☘︎ ݁˖
alisa rae .☘︎ ݁˖@RaeAlisa_·
to celebrate 3 months since lauching @lucent_ai, we're giving away 5 Codex Pro / Claude Max plans 🎁 to enter, like this post + comment which one you'd pick (codex vs claude) winners will be selected from comments in 5 days 🫶
alisa rae .☘︎ ݁˖ tweet media
English
2.1K
118
2.7K
152.1K