Creator of XcodeBuildMCP and AXe, OSS maintainer and AI optimist with occasional existential doubts.
Brighton, UK
- Tweets 15,125
- Following 690
- Followers 4,151
- Likes 5,986
With the upcoming reset, I’ve got Astra running on fast mode in ultra reasoning. Need to get as much out of it as possible prior to the reset haha.
1
5
723
Just released Skill Manager 1.1!
Skill Manager 1.1 adds an option to keep slash commands for skills you've turned off. Switch it on in Settings › General and they still run as /skill-name in Claude Code, but stay out of Claude's context until you type them.
Also lots of other refinements, bug fixes and improvements.
vibeslopsoftware.com/skill-m…
Introducing Skill Manager.
Your coding agent loads every skill's description, whether it's needed or not wasting precious context and potentially loading conflicting skills.
With Skill Manager you can switch skills on and off one at a time, group them by theme either manually or by using the AI auto-group feature, and toggle with just two clicks from the menu bar.
Skill Manager also scans your skills for potential issues, and can even perform an AI review for those more complex of issues.
Works with Claude Code, Codex, Cursor and more.
Download for free from vibeslopsoftware.com/skill-m…
2
2
18
2,851
The phone call thing is a bit weird. It’s not a real phone call and doesn’t appear to use the phone call API on iOS which apps like WhatsApp and etc use. It’s just a simulated phone call using ChatGPT’s live voice mode feature.
35
3
204
28,343
My feed is full of posts about Dots, yet because I'm in the UK I can't try them. Maybe just maybe regulatory issues could be resolved before launch. Maybe I'm asking too much.
18
44
5,056
Opus 5.5 is a really nice model. I think it could be my new favourite (for now). Just talks plainly, is very good at app dev, computer use is good (not as slick as ChatGPT). Just seems a good all rounder. GPT models just seem to over complicate everything.
7
39
2,596
Google has re-entered the room.
Announcing Gemini 4 Argon, our new frontier model.
Argon is built to sustain deep reasoning across complex, long-horizon workflows and delivers frontier performance in complex workflows across real-world software engineering, enterprise knowledge work like legal and finance, and cybersecurity defense.
We’re also expanding the model’s output token limit to an industry-leading 1M tokens.
Argon is currently rolling out to a set of trusted cyber defenders in the Fairwind Program, with broader availability as soon as possible.
8
2,232
Introducing Skill Manager.
Your coding agent loads every skill's description, whether it's needed or not wasting precious context and potentially loading conflicting skills.
With Skill Manager you can switch skills on and off one at a time, group them by theme either manually or by using the AI auto-group feature, and toggle with just two clicks from the menu bar.
Skill Manager also scans your skills for potential issues, and can even perform an AI review for those more complex of issues.
Works with Claude Code, Codex, Cursor and more.
Download for free from vibeslopsoftware.com/skill-m…
Made with AI
28
22
254
21,230
I don’t know about you but the announcements of Dots and Decisions API feel like rush announcements and things they haven’t been working on for very long. Seems they are scared of the competition to the point they will announce things barely finished. What a future we live in.
4
1
40
3,897
Just to follow up from this. I do now have the credits. Probably would have been a better execution if they had added the credits prior to sending the email account.
Just got this email from OpenAI.
It claims that I now have access to Dots which I don't because the email forgets to mention it's not available in the UK.
It says I'll see $2500 in credits in my account as a thank you, I don't see any credits in my account. Also the credits expire 3 months time.
It says that my 20x plan is now 10x plan, but I can use Sol 6.1 which is more efficient. But fails to mention that all the other models are not equally more efficient i.e. using Astra and other models will now be 50% less generous than previous.
But it's okay I can just spend £500pm (£6000 a year) to get my original usage quota.
What a Dev Day LOL.
1
4
2,023
The mistake OpenAI made was announcing the 20x Pro plan change one day before Dev Day. Feels like a rookie error.
3
5
1,194
Just got this email from OpenAI.
It claims that I now have access to Dots which I don't because the email forgets to mention it's not available in the UK.
It says I'll see $2500 in credits in my account as a thank you, I don't see any credits in my account. Also the credits expire 3 months time.
It says that my 20x plan is now 10x plan, but I can use Sol 6.1 which is more efficient. But fails to mention that all the other models are not equally more efficient i.e. using Astra and other models will now be 50% less generous than previous.
But it's okay I can just spend £500pm (£6000 a year) to get my original usage quota.
What a Dev Day LOL.
83
38
912
51,615
What a surprise, MCP wasn't bad after all. Like myself and a few others said, MCP was never the issue the integration was. I said at the time, the spec never dictated that harnesses needed to dump all tools into context. Everyone copied each other and never considered the scale issue, and then blamed the MCP protocol itself. MCP always made sense as a contract for how harnesses expose external tools to agents.
A pretty big change is that Pi now has MCP at the core. How is this even possible? What made us change our way? earendil.com/posts/you-said-…
4
24
3,538
Let's be honest, OpenAI want vendor lock-in, all these collaborations, plugins, all the features they have announced, they want to run your life. Do we really want that kind of future? They say they care about Open Source models but there is little proof of that. I'm feeling more and more uneasy about where things are heading.
At first it was exciting, it felt like OpenAI was the new Apple. But they want to disrupt every part of your life. They will know everything about you, everything you do and work on and as we've seen how they put up prices at a moments notice just when you've committed to using their tools.
We really need the open weight models to step up their game. I honestly am starting to feel uneasy about this industry, SWE has been ruined by AI, crafting software is no longer fun, prompting an AI is just boring and depressing in professional contexts.
I also feel like all these Open AI announcements are made in a massive tech/AI bubble. The average user doesn't give a sh*t about AI bots. I think we will start to see push back from the general public about the onslaught of AI on our day to day lives.
I don't know if I want to be part of this. Anyway I'm staying true to my bio as an "...AI optimist with occasional existential doubts." just feeling less optimistic of late.
17
5
89
30,563
An honest review of Dots, you won't see many of these on your feed today! Good job @RayFernando1337
I’ve had early access to OpenAI dots and I’m not here to join in on the glaze fest. Is this a Grok Bot or Hermes killer right now? NO. But…Spaces and allowing agents to thrive in apps feel like the right direction for these agents.
•• The Good
What worked well during my usage was how proactive the agent is right from the start with my existing plugins/connectors. The team is shipping insanely fast and have been quickly making changes to fine tune this experience.
•• Caveats
With a slow internet connection in the middle of the South Pacific Ocean I didn’t have a good enough connection for voice and had to heavily rely on cloud. There were other quirks related to this that might be noise but worth mentioning.
•• Bad at Writing
I tried connecting my dot to GitHub and it performed a research task to make a Spotify wrapped + story about my weeks at sea where I made over 294 PRs and shipped over 30 releases. The design felt very GPT-4 like with lots of text and the story was even worse.
•• Conclusion
I need more time with this and need to get this hooked up on my Mac at home with Codex so my dot can fly. I think there is potential to have a dot like this have access to powerful tools, web, and apps like Space to write pages and interact with humans.
I love the ease of use and speed of Grok Bot a lot. It is so fast to spin up many bots and have them quickly work together especially now as a team.
I’ll also be doing a deep dive of Grok Bot vs dots and continue to share my honest insights as a solo engineer building software after leaving FANG.
•• Disclosure & Philosophy
I hate it when I read early access posts and they only share the good but leave out the quirks. As a fellow engineer who’s shipped to billions of people, I respect the engineers who build software and spend many hours away from their friends and family to build their life’s work. The views and opinions are from me. I have not been paid or compensated by OpenAI, in fact, I’m still a paying customer and haven’t received any compensated plans from OpenAI as of the writing of this post.
As part of the Dev Early Access I plan to continue to gift my expertise, opinions, be it good or bad, with the intention that they also value their product enough to make improvements for the broader community.
1
3
11,242