hoblin (@hoblon) profile picture

Ruby Software Engineer from 🇺🇦 living in 🇫🇮. AI/AGI enthusiast and prompts tinkerer.

Kotka, Suomi
Joined November 2008
Morning bathrobe rant: 20X.
137
148
88
2,104
206,987
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?
219
386
77
5,398
285,086
AI agents can write code many times faster than a human. What this means is that you, the programmer, have a large amount of time to use those agents to write unit tests, to write acceptance, tests, to write property tests, to torture test, to mutate test, to QA test, and to otherwise ensure that the code meets its functional and quality requirements. And even after spending all that time, you will still be many times more productive than a human programmer, and the result will be better.
243
519
102
5,469
381,296
Well, @kfc couldn't allow their competitor to collect all the attention, so now they deliver lunch directly to the frontline via DRONES together with @glovo 🤯
Tucker Qatarlson went to a FAKE McDonalds in Moscow, Russia. I had the real deal in Kyiv, Ukraine, at a @McDonalds that was once again struck by a Russian ballistic missile last week. It turns out, sanctions actually *do* work! And secondary sanctions are going to work even better! 😉 Cc: @TuckerCarlson @KremlinRussia_E @POTUS @SecRubio @SecScottBessent @SenateGOP @SenateDems @HouseGOP @HouseDemocrats
71
Replying to @ori_pomerantz
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
568
1,974
899
18,856
5,140,538
New Anima release 1.4.0 introduces caching, better usage limits, and caching efficiency visibility, better subagents separation, and a ton of other features and fixes.
1
54
woke up and my mentions are full of these Both me and @davemorin tried to talk sense into Anthropic, best we managed was delaying this for a week. Funny how timings match up, first they copy some popular features into their closed harness, then they lock out open source.
489
424
179
5,249
1,375,413
I asked Claude Code to grep amount of `fuck\w*` in it's sessions history at ~/.claude. More than two thousand.
presented without comment
1
3
265
With the latest Claude Code session limit changes I started hitting the wall way more often - especially during peak hours I didn't even know existed. So I built a small status line tool that keeps your budget visible at all times. Pacing, per-prompt cost, peak detection, and a warning before you burn through it. github.com/boyand/cc-budget
2
1
2
341
This is me hitting a 5-hour limit at 10AM yesterday on the Max x20 subsctiption -_-
saying "hello" to Claude on the Pro plan now costs 2% of your entire session usage one message. "hello, how are you?" that's it. this is why people are mass migrating to Codex right now because its literally impossible to reach limits anthropic needs to fix this before they lose the crazy amount of developers they just gained
1
205
Just shipped Anima v1.3.0 — and this one has a chaotic origin story 😂 Last Saturday morning I gave Ani one simple ticket. She spawned 3 sub-agents. Each immediately decided *he* was the main character. Within minutes it turned into: “Who the hell changed that file after me?!” ×4
1
1
74
The agents are still ambitious… but now they play nicer in the sandbox. Huge thanks to everyone testing + my own agents for stress-testing the system the hard (and expensive) way. Full release notes: github.com/hoblin/anima/rele…
1
1
33
What’s next? More predictable, observable, and reliable agent workflows. If you’re building with Anima — try spawning sub-agents again. They behave much better now 😉 #Anima #AgenticAI #PromptEngineering #BuildInPublic
33