Principal Engineer | AI Tinkerer | Contrarian
India
- Tweets 3,424
- Following 164
- Followers 360
- Likes 47,974
Pinned Tweet
Building something with @mattpocockuk's grill me skill, and to say I'm at my wit's end would be an understatement
How many more do you have for me bro?????
3
81
75,893
By popular demand, I'm shipping v1.3 of my skills today.
Too much hype behind /retro not to ship it.
Enjoy going back through your old transcripts and figuring out improvements.
Docs, video, and announcement post coming Monday.
github.com/mattpocock/skills…
77
129
2,359
133,955
One last thing I wanted to ask, usually we already have issues filed on JIRA(mostly vague or business only language). Our daily workflow is basically take those tickets, spec it out really well, then write those changes back to the ticket and then raise the PR for that ticket in a topic branch (with specific naming conventions). Can I describe all this while setup and it will adopt?
1
320
Dear @claudeai, you have amazing models, and you probably have even better ones available internally. Could you please ask your Super Intelligence to simply copy the UX of the Codex desktop app? Their app is obviously better.
Your quality bar for UX/design is much lower than Codex’s or Cursor’s. It would be amazing to fix that.
So far, you have a competitive advantage in the design community: your models are simply better at motion and design, so I still have to use your app for certain tasks. But it’s extremely painful to use your application after experiencing better alternatives.
43
9
251
33,717
Are there specific gaps you have in mind? We regularly look at fixing community papercuts but happy to chase UX feedback if particular.
26
36
10,881
Hermes Webapp, now on your phone 📱
Mobile update to my @NousResearch PR: hermes webapp now fits phones and tablets. The composer stays above the keyboard, Copy and More are thumb-sized, and a reply keeps streaming through a page reload.
github.com/NousResearch/herm…
50
59
720
84,587
Windows/Linux app are available now, and code mode, more plugins, custom MCP, custom providers etc
lorca.app/download
Imagine Grok bot, but open source, as a native cross-platform app, and your data is end-to-end encrypted.
Introducing Lorca.app:
5
3
42
5,076
we're seeing a lot of personal/work agents right now
muse, grok bot, dots, the og openclaw, hermes, instinct, etc
the one i used most was openclaw, and it was a nightmare to set up, even for someone as techy as me
havent tried grok bot. been tempted, but i avoid elon's products as much as i can (yes, swear at me)
dots looks fine. feels like just one more option. pricing is prob the best part, but im privileged enough that it's not a factor for me
the one im most curious about is instinct, mostly for the branding and positioning. founder seems really cool too
either way, the issue with all of them is you gotta go through the painful process of giving them access to everything. every service you use, every bit of data they need, etc
so how do you pick? ux? branding? politics? open vs closed? ecosystem?
68
127
13,423
SDG retweeted
Super excited to be interviewing @poteto, live, in ~48 hours on YouTube.
We'll be nerding out about skills, high-velocity software factories, and learning SOTA techniques for shipping with agents.
This Friday - 9AM PT. Don't miss it!
piped.video/live/MN9dGgmLyso
128
142
3,507
230,379
I wore a rosary to dev day and it was so surprisingly pleasant to see folks want to talk about faith
and about the need for spirituality in this moment of rapid speed and change in society
technology will continue to speed up exponentially. our consciousness must evolve so that we expand to navigate it
a separate thread, but I think more people than ever are derealizing and having panic attacks and experiencing psychic fault lines
it will be more important than ever to be in community & to be able to ground into meaning. into a belief in something bigger
16
5
121
5,884
I have an idea similar to dots.
Imagine you can control a personal AI assistant, but you don't have to speak to it. You can control it with your mind.
I'm going to call it...
thots
63
24
729
14,709
BREAKING: @OpenAI releases Dots, AI agents for work & life, claiming lightly bezeled 3d blobs as avatars, reducing remaining bot avatar greenfield for new startups by 30%
23
4
195
19,293
i hate that tonight feels more important than wwdc.. when i know they gonna announce a slopenclaw layer and maybe the jony ive tamagotchi bs ... makes me wanna be a contrarian and not watch it at all 💀
7
55
4,095
I saw Tibo at a grocery store in San Francisco yesterday. I told him how cool it was to meet him in person, but I didn’t want to be a douche and bother him and ask him for resets or anything.
He said, “Oh, like you’re doing now?”
I was taken aback, and all I could say was “Huh?” but he kept cutting me off and going “huh? huh? huh?” and closing his hand shut in front of my face. I walked away and continued with my shopping, and I heard him chuckle as I walked off. When I came to pay for my stuff up front I saw him trying to walk out the doors with like fifteen Milky Ways in his hands without paying.
The girl at the counter was very nice about it and professional, and was like “Sir, you need to pay for those first.” At first he kept pretending to be tired and not hear her, but eventually turned back around and brought them to the counter.
When she took one of the bars and started scanning it multiple times, he stopped her and told her to scan them each individually “to prevent any cache infetterence,” and then turned around and winked at me. I don’t even think that’s a word. After she scanned each bar and put them in a bag and started to say the price, he kept interrupting her by yawning really loudly.
214
42
3,464
504,865
i assume people are going to shit on openai for this but spending $200 to get $10k in usage isn't really a sustainable model
i care more about 'can i do my work for a reasonable price' than a specific value of the plans
appreciate them acknowledging it & having a path forward
Hi,
Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan.
Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago.
(a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want.
(b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions.
(c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent.
(d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet.
I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news.
Codexingly,
Tibo
177
16
584
62,299
