My current weird hobby is having GPT-5.6 Pro "over-analyze" things
> I want a deep character study of Bebop and Rocksteady - I want to understand their motivations, their interests, their hopes and aspirations, how they differ from each other - really over-analyze this
It’s all fun and games to vibecode a clone of a an enterprise software tool for <$500.. until you actually have to make it enterprise-grade.
Great software for large enterprises hides a lot of complexity from users. Whether it’s maintaining SSO, upgrading security / deps, RBAC, a wide gamut of config-gated features, API access, scaling, release management, integrations with changing APIs - there’s a long tail of important but boring work to really make even simple apps work well in businesses. And it usually doesn’t make sense for an Engg team to pay that recurring maintainence cost.
Companies continue to use SaaS tools like Linear, Notion, Slack, GitHub, Google Workspace, Figma, Salesforce, Workday, Glean and more.
There’s a category of tooling this makes a lot of sense for: bespoke internal tools, dashboards and one-time / few-time use tools. A founder I know famously told me “I vibecoded my own data room tool and the folks I worked with actually really liked it” or “we vibecoded a better version of my Retool customer support UI” But for most other ones, it usually doesn’t make sense.
One might argue that vibe coding ultimately reduces the cost to building competitors to such tools, and that there’s some ensuing price compression. While there might be some truth to that, a version of Amdahl’s Law still applies here. When software ceases to be the bottleneck, it becomes sales and marketing to compete. How many companies have moved off Slack since vibe coding? How many Slack competitors have even come up since 2022? Not many!
I imagine in the future, there will be a lot of cheaper less full-featured open-source alternatives for startups that will eventually try to compete. Hell, maybe models get so good that they pre-empt the need for all these features and one shot it perfectly out of the gate with a background loop that maintains it. Until then, “we’ll just vibecode it” can be a trap.
The first autonomous agent cyberattack is an unprecedented event that deserves unprecedented transparency. Today we’re sharing everything we can: a full technical timeline, an interactive replay, and how we used an open model to defend ourselves, so defenders everywhere can learn from it and prepare for what’s next.
https://t.co/uPxIpjW8Xn
I used GPT-5.6 Sol to build a multiplayer word game.
In Parafraze, give clues without saying the word while your team races to type the answers.
Grab some friends and play free: https://t.co/TOfLqTHa3j
or find it in Discord Activities, search for Parafraze!
Some people seem to be surprised that an old geezer like me could adapt so quickly to the newest tech.
The thing is, I've been a programmer for over 60 years. And every single year brings another adaptation to new tech. Adapting to new tech is what we programmers do on a regular basis. Why would I stop now?
This is why we need competition and open weights in AI. Imagine a world where only Anthropic sat as the moral arbiter of acceptable speech. Fucking ridiculous. (Grok of course did it no problem, same too with Kimi K).
Btw this is why computer science matters. Yes, you can self teach it if you really want to (I personally wouldn't have had the discipline, so college was a way better force). However you learn it, the theoretical fundamentals matter and get applied to work every single day.
Releasing the model weights and technical report of Kimi K3.
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.
Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f
“ I’m still picking up the pieces after putting my trust my heart , my money and my future in the wrong hands “
Tram’s white wifey is already calling him out for scam lmaoo . It’s about to be a long season for him
I’m sat🤣🤣
#bbnaija
This is a good post and obviously hits a nerve with folks. I think folks are rightly concerned about 'heaviness' of skills, and I have criticised other skill libraries/frameworks for being too heavy-handed.
My goal is always to make the skills as light as they can possibly be. Not only within the skills themselves, but lowering the context load of the overall approach. Small skills are easier to maintain, audit, and survive model changes better. Recent guidance on prompting Fable seems to back that up - say less to the model, and it does better.
Documents are for the model, not the human
Here's where I think you got something wrong. Every 'document' I use is designed for the constraints of models, not for humans.
Why have a spec at all? To clearly define the destination in an artifact which can then later be checked via /code-review.
Why have tickets? So that you can split work into smart zone-shaped sizes.
I'm using the terms 'spec' and 'tickets' because they are familiar to devs - not because I am trying to mimic Jira.
Wayfinder, similarly, is designed for the constraints of models. It breaks down planning into context-window shaped chunks of work.
The smart zone
If there is a bitter lesson in AI coding, it's about the "smart zone". My skills assume that working with irrelevant information in your context window is bad, and so they break work into session-sized chunks via /to-tickets.
This is strictly an AFK agent optimization - AFK agents do better with chunks scoped ahead of time. I've experimented with just a spec and /goal, but the results were worse.
As you can tell, your itch is something I think about every release of my skills. I am always trying to reduce my maintenance surface, to make the skills smaller and more useful. I often do a no-op pass on my skills to check for things the models now do out of the box.
Thanks for giving me an opportunity to articulate this! A really well-phrased question.
Having fun in Biggie's #BBNaija house? Chimsom Chuka is here for it 😮💨. The 27-year-old Anambra-born pharmacist handles pressure like it's nothing.
He’s patient, funny, and here to showcase his authenticity.
chef, a model and a certified scene-stealer.
Abi from Osun State isn't here to do background roles. She's bringing the big laughs and enough personality to season the entire #BBNaija house. With the sauce.
Catch it 👏🏾
Face beat. Confidence high. Patience for insults low.
Flora is a fashionable makeup entrepreneur with honesty and enough spice to keep the #BBNaija house on its toes. Her love life? Complicated.
He's a bundle of talent, and he knows it 👀 23-year-old Lagos on-air personality Gerard is the wild card of the #BBNaija house — an open book who hates dishonesty and is here to live every moment to the fullest.
Gym lover. Proud mom. Lover girl. 🥰
Sheba is bringing her powerful voice, warm energy and an open heart into Biggie’s house.
Meet the woman who is here for good times and possibly love. #BBNaija
Bad boy by necessity, that's Ricky 😮💨 33, Port Harcourt writer, finds love as thrilling as he finds literature, yet he doesn't subscribe to it.
#BBNaija
He’s a self-starter who is highly confident in himself.
25-year-old Yusuf from Kogi, an actor, is bringing his energy, honesty, unpredictability, and a whole lot of emotions. He’s ready to add Loverboy to his title, because he’s big fan of love.
#BBNaija