Viewing profile — efromvt

I think the context here is that em dashes are usually generated verbatim from LLMs? I haven't seen them generate a lot of double hyphens; I suppose the post could be laundering th…

I finished wiring up the backend data merge so user(s) (aka me, really) can record trees as they walk and have those merged into the general city data on my urban tree map app[1]. …

They actually touch on Blue Prince in the article; it is interesting that Expedition 33 isn't driving investment in similar sized games. But the thesis seems to be that Blue Prince…

Either they had a good month or I'm off my game, I actually spent a minute checking if I did something wrong with actions instead of immediately going to HN to see if it was an out…

It’s an interesting question of ‘why not’, though - this was a good read and is upstream of more practical output optimization.

I’ve historically read this as ‘open format compatible’ but ‘native preferred’ - where this opens up market space and dev velocity - but it’ll be interesting to see if native stora…

The system needs to account for how it will be used and resulting externalities. Being an accelerant can be a problem in and of itself. I do agree that having stricter societal and…

This has been a soul crushing part of the AI craze - we can finally fund all the devx work we wanted to do, for all the wrong reasons. (It is nice that I can make something try our…

Praise be, stacking is such a better ux for separating out a feature diff into distinct component units and native support makes it easy.

Isn’t the intentionality the actually concerning bit? Exploit capabilities are all fun and games constrained by the humans directing them; a paperclip maximizer going rogue with th…

I think/hope that most benchmarks have moved to an agentic loop - I'd still call that 'text to sql', since you're going from the business question to one or more SQL queries that p…

Yeah with self-serve analytics all the rage (for good reason) for a bit, the bar from some places I've worked wouldn't be "does the agent beat a good analyst" it's "does the agent …

This was a very enjoyable read! Constraining the language surface is helpful, but the lost expressiveness can bite unless you’re in a constrained domain - which this seems like it …

I’ve noticed it having weird message dropping and replay in general, but the compaction boundary has been pretty solid.

This was more interesting/creative than I expected on both sides (the prompt and the existing safeguards). I love that obscure Cloudflare validation turnstiles seem unsuspicious ba…

DSLs are a great middle ground for 'use LLM to turn ambiguous spec into something well defined', with the caveat that without discipline they'll inevitably expand until you should …

I think like social engineering, it will always be an issue to some degree, and we'll build safeguards until it's at a 'societally comfortable' baseline level. Which is maybe not p…

Same as last month for once - optimizing how well agents can work with a new language [1]. I've been able to 2-3x success rate and drop total tokens for complex tasks significantly…

I guess technically it is in the SQL standard, but optional, as S098? I agree that SQL is sorely lacking here and I'm hoping that the OLAP side innovation (presto, bigquery, snowfl…

never use system python, always use virtual envs. (a bad answer, but agents do remove the setup boilerplate). UV does relatively completely solve this but it's a big dependency to …

Out of curiosity, how often are the resource limits the bottlenecks? What do harnesses do to help here - limit parallelism? More efficient tools?

Second comment, having read in more depth (really love the auto-layout detail!) - the spec doesn't seem to naturally support layering (which is useful in some multi-axis automatic …

Op1M5 was scarring the first (dozen) time around! Thank you minelayers

I wonder if all those different heavy shenanigans are just to get the hollander's gauss/hunchback autoconnon in the right torso by default. (original Mechcommander is still the bes…

Semantic types as the extra formatting factor is super useful because they are concise encodings of a lot of formatting boilerplate.[1] Do you envision the flint type registry bein…