🙋♂️ SWE @ServiceNow 👨💻 Talks to software & cats 🐈 I read Research papers so you don’t have to ✍️ PhotoJournal & Doodles are my thing 🧑🎨
Joined April 2021
- Tweets3.8K
- Following1.1K
- Followers567
- Likes9.2K
Pinned Tweet
Building cool shit with AI and posting about it ✍️
Currently:
🤖 Going all out on Model Context Protocol
🤓 Diving into Deep Learning & research & sharing fundamental insights
🚢 Creator of MCP Maker & Adam Ascension (game)
📑 Published research paper on Recommendation Systems
🧡 Learning in public & sharing the journey 🛣️
☀️ Day: SWE @ServiceNow
🌙 Night: Everything else
Follow along if you want to see what’s possible when you just start building 🛠️
Here’s what you need to know about Pele 👇
xitter.cf/kepano/status/21114720…
i've been a bit quiet - working on a new companion skill that will help your agents draw these beautiful statecharts/diagrams + check them against the specs you made with /create-formal-verification-skill in pstack!
it now uses Pele from @kepano too which is why they look so good.
will release soon!
agentic development increases speed of delivery,
but upto a threshold only.
you can not surpass the upper limit governed by speed of human understanding.
codewithP 🔳 retweeted
I've been trying to keep up with ai-driven-development, and its hard to keep up with the pace.
I've learned some ways to conquer this change of tempo, and I think it'll be useful to you too 👇
dev.to/prakh_r/when-ai-write…
#DEVCommunity @ThePracticalDev
/retro & /writing-for-agents are my most used skill. Agents no longer rediscover everything from scratch.
Thanks @mattpocockuk
Throwing in Muse 1.3 Contributor in the pit of Cheapest ranked by intelligence ( @ArtificialAnlys Index)
I've been trying to keep up with ai-driven-development, and its hard to keep up with the pace.
I've learned some ways to conquer this change of tempo, and I think it'll be useful to you too 👇
dev.to/prakh_r/when-ai-write…
#DEVCommunity @ThePracticalDev
codewithP 🔳 retweeted
NEW Haiku 5.5 is the death of Haiku tier
Haiku now operates like ~Sonnet
Sonnet now operates like ~Opus
Opus now operates like >=Fable
Fable 5.5 will be a new day in the AI world
If you’re using matt pocock skills & are confused on wayfinder
This’ll help
Should you /grill-with-docs, /wayfinder, or just one shot the code?
1. If the diff is tiny, DON'T grill
/grill-with-docs saves you from situations where the agent built the wrong thing. But if the thing it's building is tiny, that cost drops to nothing. So one-shotting is absolutely fine when you're only making small changes.
2. Never start with /wayfinder
A failure mode of /wayfinder is that you start grilling and the solution turns out to be way simpler than you thought. Why is this bad? Because you've created the map and tickets, and you realise you don't need them.
So if the expected diff is medium-large, always start with a /grill-with-docs session. Then, if planning starts to get out of hand, just say "/wayfinder let's turn this into a map".
Gonna use @StepFun_ai Step 5 for recommendation research via @NousResearch Hermes
Let’s see how it goes
Haiku 5.5 is a tremendous improvement.
Here's a comparison with GLM 5.3 Flash to put things into perspective 👇
artificialanalysis.ai/models…
if you're not following @poteto vs @thsottiaux showdowns
you're missing out on quality stuff 😛
botsvsdots.com/
The @poteto vs @thsottiaux beef has been fun to follow, so I vibe coded a site to turn it into a proper battle.
Each X thread is a round. Likes decide who wins. You decide who wins. Everything updates in real time.
botsVSdots.com
Enjoy!
codewithP 🔳 retweeted
1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!
fat kitty is here
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.