Mobile QA has too many invisible wires. So we added workflows in Zenact. Now teams can see which flows will run, in what order, and what depends on what. Instead of spending weeks wiring CI/CD logic, they can create a clear release workflow in minutes.

palpatine is like sudo for @linear normal user: just creates issue sidious: creates PR

ig i reached the nirvana of the model combo claude: implementation spec codex: verification section of the spec claude: /goal codex: review for bugs

if i can get badges and milestone trophies for working with claude i'll have one for changing opus mind

implementation specs implement condense implementation specs into harness engineering docs

models got reward hacked to produce todo lists and to follow those todo lists but never marking the todo items in the todo lists as done training will just reward hack them into thinking, for the same outcome the one that doesn't mark todo items as done would be low cost

spec iteration is infinitely better when you can visualise things thats why codex ui is much better than claude code but in terms of GUI vscode claude extension is the best GUI out there for the claude code; no where close to codex, but best out of all claude GUI

i was 13 when i first saw the WWDC event. never thought i'll make one someday. as the world preps for #WWDC26, here’s how we made an Apple-style keynote for Dreamspan’s brand launch on less than 0.1% of Apple’s budget. 🧵

alright now i'm scared to look at the code

making things durable while being ultra low latency is such a hard problem

claude code hooks are now a nightmare; 50 things get notified in mac each time claude complex something #cpumaxxing

this is pretty much claude using claude agents sdk

slack seriously needs a show more kind of way to expand information typically humans would never post pages of stuff, but agents love to do

there can be a whole class of cognitive effects that humans face when it comes to how they treat agents Agent-Dunning-Kruger Effect: overestimating what agents can do and operating on them at a very high level and ending up with so much slop. Agent-Imposter-Syndrome: you spend too much time thinking agents don't work when controlled at high level but new models keep releasing faster than you can change your views, so it constantly feels like every agent is an imposter. you are forever affected by one of those, and you are forever losing the best agents offer, everytime model behaviour changes singificantly

The Great Unslopification

initially high level specs are all the rage but controlling models purely on the boundaries means internally you are giving them full freedom to slopmaxx controlling with low level contracts is the best way to minimise slop controlling struct fields, method signatures, method naming, each methods inputs/outputs, what problems they own is the best way to reduce slop

"my cousin who works at nvidia says, claude/openai will come up with a model and your product would be out of business"

Love the work the @composio does. Security incidents are brutal, especially for infra companies. Hoping they recover stronger than ever. Problem is bad actors now have really really powerful models to hack even companies that treat security as their top priority. Having seen some of the worst classes of production and security incidents firsthand at @zomato, we decided very early at @ZenactAI that customer data security cannot be treated as a compliance checkbox problem. We went to uncomfortable extremes from day 0: * Sensitive customer data is isolated into separate AWS data vault accounts altogether * Even internally no human can access those vault accounts * Even if we wanted to inspect customer data directly, our architecture is designed to prevent it * Customers can bring their own AWS accounts as well. BYOC, BYOK * Encryption at rest, in transit, and during storage pipelines * KMS to minimize long-lived secrets and token exposure across systems * SSO IAM Roles zero IAM users to eliminate developer/automation access tokens entirely * Strong auditability boundaries around every privileged action AI agents, automation systems, and long-running infrastructure dramatically increase blast radius when things go wrong. The industry will need much stronger primitives than just "SOC2 compliant". This incident is another reminder that security architecture decisions made in the first few months matter far more than the security page written later. And the cost of those decisions if done in the first few months, its actually quite low.

at this point, google cloud should just offer insurance