Samarth Aggarwal

Search & Intelligence @Glean. Formerly @meta AI, @adobe research, @quadeye, @IITDelhi CS, @UofIGrainger CS.

[Samarth Aggarwal @Samarth_A]

@nicochristie one could say beyond a certain threshold of difficulty, latency stops mattering coz you're like take a full hour but solve this problem? arguably, mythos-level intelligence is only needed for tasks at that level of difficulty. wdyt?

[Samarth Aggarwal @Samarth_A]

@handotdev @mintlify insane flex

[Samarth Aggarwal @Samarth_A]

@rauchg so true, you need to be a software engineer to ensure AI agents can vibe code sustainably. What's a good metric to measure judgement for engineers and projects?

[Samarth Aggarwal @Samarth_A]

@snowmaker but this assumes users know and can express what they want, which is arguably harder than navigating a "well interfaced" website.

[Samarth Aggarwal @Samarth_A]

@beyang absolutely, even highlighting diff within a line

[Samarth Aggarwal @Samarth_A]

@thsottiaux managing git worktrees needs to be easier via codex

[Samarth Aggarwal @Samarth_A]

@jxnlco any tips on updating your AGENTS.md (et al) so that codex learns your preferences over time? so far, I ask codex any learnings you'd like to add to agents.md after a long session. but I want something more automated and continuous.

[Samarth Aggarwal @Samarth_A]

@pk_iv 100%. any accountability building practices you can share?

[Samarth Aggarwal @Samarth_A]

@sakurayukiai curious why you say this was "by accident"?

[Samarth Aggarwal @Samarth_A]

@nikitabier Please add reading time estimate to X articles. Over time, it should be personalized to a user's reading speed and propensity to quickly scroll the genre.

[Samarth Aggarwal @Samarth_A]

@nikunj As you alluded in "explore all edges" - exploratory budget should be pretty high but prod budget needs to be capped. Mixing the two leads to unjustified spend.

[Samarth Aggarwal @Samarth_A]

@patpcj Your product video looks very polished, kudos! Curious what tool you used to create it?

[Samarth Aggarwal @Samarth_A]

@nikunj @meetgranola curious what you think will be the skill gap buckets even after 100s of iterations?

[Samarth Aggarwal @Samarth_A]

@matanSF @matanSF is displacement/churn in top3 open-source models higher than closed-source ones?

[sahil dhull @_sahildhull]

the input interface has been the same for decades.

with ai, software can now reason and act on your behalf but the interface is the bottleneck.

why do i have to check sushi on 10 restaurants across 3 apps? why can't i just do it with a flick of a finger?!

the world's about to get a new interface @agi_interfaces

[Samarth Aggarwal @Samarth_A]

@nikunj the perf difference b/w models on benchmarks is not high enough to justify switching costs (claude.md, muscle memory, skills, etc.) for me. If and when it becomes high, I'd definitely try a new model.

[Samarth Aggarwal @Samarth_A]

@andrewchen spreadsheets are easy to verify. that made mistakes easy to catch. as spreadsheet users become vibe-coders without the skill to verify the generated code, there will be a plethora of undetected errors.

[Samarth Aggarwal @Samarth_A]

@nikunj any process with handoffs feels like a game of telephone now

[Samarth Aggarwal @Samarth_A]

@trq212 read existing claude.md and suggest improvements coz it tends to get bloated over time if multiple people in a repo are contributing to it.