Viewing profile — magospietato
magospietato
HN member- Joined
- Wed, Nov 13, 2019, 9:34 PM UTC
- HN karma
- 208
- Public activity
- 73 items
- HN profile
- View on Hacker News ↗
About magospietato
No profile information was provided.
Recent public activity
-
comment
Comment #47653262
Haven't built anything on the agent skills platform yet, but it's pretty cool imo. On Android the sandbox loads an index.html into a WebView, with standardized string I/O to the ha…
-
comment
Comment #47534790
It's not that the context window is adequate, but rather an agentic LLM can search the source of truth using appropriate tools (SQL, term search, etc.) RAG made sense when the sema…
-
comment
Comment #47447682
Living here the decline is tangible. And this is West Oxfordshire; not one of the poorer parts of the country. An example in microcosm: a local village suffered road flooding due t…
-
comment
Comment #47401473
Context caching deals with a lot of the cost argument here.
-
comment
Comment #47393778
Con: from 2016 w. no followup?
-
comment
Comment #47258474
Surely the skill for a cli tool is a couple of lines describing common usage, and a description of the help system?
-
comment
Comment #46906501
Expires after 60 days per the link. In case you're thinking of stretching it out beyond a couple of months.
-
comment
Comment #46835039
Complete aside, but it's beyond infuriating I need to enable a VPN here in the UK to view this link.
-
comment
Comment #46819157
Having seen a family member die absolutely horrifically in a matter of weeks due to late-diagnosed pancreatic cancer, I'd consider suicide if I got the same diagnosis.
-
comment
Comment #46819047
I wonder what training insights could be gained by having proven general intelligences actively navigate a generative world model?
-
comment
Comment #46819013
Always wondered if dreaming is some kind of daily memory consolidation function. Logged short-term/episodic memory being filtered and the important bits baked by replaying in a lim…
-
comment
Comment #46689076
I'm copacetic to the notion we're not at enterprise codebase level (yet), but everyone who still thinks agentic coding stops at React CRUD apps needs to update their priors. I need…
-
comment
Comment #46525507
I still manually approve tool use requests at the start of a run. As it gets deeper in I might allow it to run safer commands without that oversight (e.g. writing to local text fil…
-
comment
Comment #46524400
Possibly Codex, but I've only used Claude Code so far. Worth pointing out I'm not SSHing to a different device. Claude Code installed and running directly in Android terminal on my…
-
comment
Comment #46519927
This is how I do mobile device coding. Android terminal w. git and gh installed and authenticated. Claude manages the feature branching and PR process; I review the PR in the GitHu…
-
comment
Comment #46519851
I'm using the Android terminal and Claude Code to vibecode on the go. Or rather, as a fairly boring father of two, when I'm tied up in the necessary chores of family life - cooking…
-
comment
Comment #46212408
Wow, that's brilliant. Can't help but think your script unlocked this. I'm now genuinely reconsidering whether frontier LLMs can't act as force-multiplier to general creativity lik…
-
comment
Comment #45443799
Whitehall - the UK civil service - persists between governments in a fairly unique way. It's essentially a political entity that exists beyond democracy that has pinky-promised to …
-
comment
Comment #45340362
I'm confident you could build one of these in an IF engine like Inform, but the offering is fundamentally different. These books are essentially compressed TRPG experiences where t…
-
comment
Comment #45340329
I've literally just started replaying/rereading these with my 9yo son. It's been eye opening. A book that allows you to _do things_ is finally a challenge to the allure of the tabl…
- comment
-
comment
Comment #45178128
YouTube music being included effectively replaces an additional music streaming service. From that perspective the family oriented plans in particular carry a lot of value.
-
comment
Comment #44970099
This tracks with my career - highly goal oriented and highly stressful until I sacked it all off for a less intense, more code-focused role a couple of years ago. What I will say i…
-
comment
Comment #44927687
https://en.m.wikipedia.org/wiki/Barnacle_goose_myth From our late scientific-era perspective it's really difficult to appreciate how badly intuitive understanding of cause and effe…
-
comment
Comment #44927659
There is a quiet poetry to GPT1 and GPT2 that's lost even in the text-davinci output. I often wonder what we lose through reinforcement.