Ivan

Software Engineer. Interested in system design and hammock-driven development. Edinburgh walker.

[antirez @antirez]

Simple way to evaluate an AI frontier lab ethics / company culture: attitude towards the user base in the time spans they have the best model.

[Ivan @ivanbokii]

@fatih A long while ago, @colmmacc recommended "Designing Distributed Control Systems: A Pattern Language Approach" book for learning about system design/architecture of control systems. Would appreciate any great recommendations from you on this topic 🙏.

[Kitten 🐈 @kitten_beloved]

This is like one of those audio journals you find on a corpse in a sci-fi horror game

[Mario Zechner @badlogicgames]

rick beato is jow part of the local inference open weights underground.

this timeline is killing me.

https://t.co/Cd3ps5baQg

[Jo Kristian Bergum @jobergum]

Two announcement events recently that I simply don't get.

Amp (a coding agent tool) declaring coding agents as dead.

Linear (a issue tracking tool) declaring issue tracking as dead.

[François Chollet @fchollet]

This is more evidence that current frontier models remain completely reliant on content-level memorization, as opposed to higher-level generalizable knowledge (such as metalearning knowledge, problem-solving strategies...)

[Joscha Bach @Plinz]

@AnnaLeptikon Computers used to be unforgiving. I wonder what will happen if the next generation of computer scientists does not grow up with “syntax error in line 20” but with “you are absolutely right, let me try…”

[Jessie Frazelle @jessfraz]

I give it less than 6 months before Garry stops preaching LOC and starts preaching maintainable code bases.

And with that one move he will go from junior engineer to a bit more senior.

We watching his Eng journey live 🍿

[Ivan @ivanbokii]

@headinthebox It seems you're conflating skepticism about AI as a technology with a criticism of the current state of AI coding.

[Ivan @ivanbokii]

@headinthebox @darin_gordon Anyone practicing AI/agentic coding on a daily basis sees how AI struggles to maintain its own code due to quickly compounding complexity. You'd have to assume AI is a perfect coder to deny this. Obviously a flawed assumption.

[Ivan @ivanbokii]

It’s quite unfortunate that GEPA Optimize Anything didn’t get enough traction, while very, very similar ideas promoted by Karpathy’s autoresearch + Lütke’s pi-autoresearch - got so much traction, despite being less general

[Ivan @ivanbokii]

@fatih Concave with replaceable switches would be the dream, but afaik there's no good way to make it work, specifically because of the shape. I ended up manually resoldering switches on the 2/360 for the same reason - the stock switches are just plainly bad. Thank you for the reply 🙌

[Ivan @ivanbokii]

@techdevdaily @mitsuhiko @thekitze I think it’s a general social media psychosis. “fuck everything… lock in… generational wealth” - a weird x/AI distortion of reality.

[Ivan @ivanbokii]

@jnardiello @fatih @RepoPrompt has implemented a very nice approach using managed file selection, which forms the context exposed to the pairing models through a standalone tool that is part of their MCP server

[Ivan @ivanbokii]

@jnardiello @fatih for coding, how exactly the context is shared between the main driving model and models exposed through zen mcp? I.e. if the main model already traversed the filesystem and collected required code, how's this code shared with "pairing" models?

[Ivan @ivanbokii]

@pvncher @RepoPrompt @claude_code Eric, how's this different from a regular grep tool already available to cli agents?

[Ivan @ivanbokii]

@pvncher @RepoPrompt What’s the point of exposing navigation and editing through RepoPrompt when CLI agents already have their own toolsets? You can also tap into 2.5 Pro from Claude Code using "gemini -p" already. It’s almost like CLI tools have made your PMF redundant.

[Ivan @ivanbokii]

@pvncher @RepoPrompt I feel like CLI tools like Claude Code, OpenCode, AMP, Gemini-CLI have made RepoPrompt a bit redundant. It seems like you’re pivoting hard from a tool that composes context for AI web chat interfaces to an MCP server that’s primarily useful for people who aren’t using CLI agents.

[Ivan @ivanbokii]

ugh, forgot to mention that I'm referring to Claude Code and not the web interface

[Ivan @ivanbokii]

Hey @AnthropicAI folks, I’m on $100 Claude subscription, and I just started my 5hour window but already seeing “Claude Opus 4 limit reached, now using Sonnet 4.” Had a similar experience yesterday. I understand that Opus 4 counts 5x in terms of consumption, but it’s clearly off.