Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agents that run while I sleep

claudecodecamp.com

Post reply on HN
Print view View original

391–400 of 532 posts

Re: Agents that run while I sleep

#391

Post by hparadiz »

Imustaskforhelp wrote: post #385
skeledrew wrote: post #335

Earlier quoted context omitted.

I think the point here is that the scaling problem is hard because of PHP.

Scaling can be hard in PHP at the same time GGP comment's about PHP being in productive hands and thus being one of the reasons why PHP worked for them. Both of these can be true at the same time. And for what its worth, Typescript scaling, although better than PHP is still somewhat of an issue and If you want to have massive scaling, Elixir/ (to-an-extent gleam) are developed for solving the scalability problem espe…

Scaling in PHP is easy. Has never actually been an issue in my entire career unless it was a badly designed database.

Re: Agents that run while I sleep

#392

Post by siva7 »

godelski wrote: post #263
hi_hi wrote: post #206

This _all_ (waves hands around) sounds like alot of work and expense for something that is meant to make programming easier and cheaper. Writing _all_ (waves hands around various llm wrapper git repos) these frameworks and harnesses, built on top of ever changing models sure doesn't feel sensible. I don't know what the best way of using these things is, but from my personal experience, the defaults get me a looong wa…

I can't believe we're back to advocating for TDD. It was a failed paradigm that last few times we tried it. This time isn't any different because the fundamental flaw has always been the same: tests aren't proofs, they don't have complete coverage. Before anyone gets too confused, I love tests. They're great. They help a lot. But to believe they prove correctness is absolutely laughable. Even the most general tests a…

TDD and similiar test paradigms have all the same fundamental flaw -> It's testing for the sake of testing. You need to know exactly what you want in order to start, which isn't compatible with a competitive iterative workflow no matter how much TDD yells otherwise. TDD doesn't make sense in agile and fast iteration workflows, only in heavily regulated / restricted products.

Re: Agents that run while I sleep

#393

Post by silentsvn »

uxcolumbo wrote: post #294
silentsvn wrote: post #87

One thing I've been wrestling with building persistent agents is memory quality. Most frameworks treat memory as a vector store — everything goes in, nothing gets resolved. Over time the agent is recalling contradictory facts with equal confidence. The architecture we landed on: ingest goes through a certainty scoring layer before storage. Contradictions get flagged rather than silently stacked. Memories that get rec…

Sounds interesting, would like to learn more about this. How do you imokement the scoring layer and when and how is it invoked?

The scoring layer sits between ingestion and storage. Incoming items get evaluated on a few axes: source reliability (did the agent observe this directly or was it told?), semantic distance from existing memories, and recency weighting for time-sensitive facts.

Contradiction detection runs as a separate step - we embed the incoming memory, similarity-search against existing ones, and score the pair for logical consistency. If it trips a threshold, it gets stored with a conflict flag and a link to the contradicting memory rather than silently overwriting.

The agent sees both during retrieval and reasons about which to trust in context. Sounds like overhead but it's fast — the scoring is a simple feedforward pass, not another LLM call.

Re: Agents that run while I sleep

#394

Post by oliver_dr »

rwmj wrote: post #379
ruszki wrote: post #358

Earlier quoted context omitted.

Even cutting edge models are not very good. They are not even on mediocre level. Don’t get me wrong, they are improving, and they are awesome, but they are nowhere near good yet. Vibe coded projects have more bugs than features, their architecture and design system are terrible, and their tests are completely useless about half the time. If you want a good product you need to rewrite almost everything what’s written…

Not sure why you're being downvoted, this is very much my experience. When it matters (like, customer data is on the line) vibecoded projects are not just hilariously bad, but put you in legal danger. We've so far found that Claude code is fine as a kind of better Coverity for uncovering memory leaks and similar. You have to check its work very carefully because about 1 time in 5 it just gets stuff wrong. It's great…

[dead]

Re: Agents that run while I sleep

#395

Post by silentsvn »

girvo wrote: post #198
silentsvn wrote: post #87

One thing I've been wrestling with building persistent agents is memory quality. Most frameworks treat memory as a vector store — everything goes in, nothing gets resolved. Over time the agent is recalling contradictory facts with equal confidence. The architecture we landed on: ingest goes through a certainty scoring layer before storage. Contradictions get flagged rather than silently stacked. Memories that get rec…

Interesting. I’ve been playing with something similar, at the coding agent harness message sequence level (memory, I guess). I’m looking at human driven UX for compaction and resolving/pruning dead ends

Human-driven compaction is interesting — you sidestep the "what's worth keeping" problem by putting a person in the loop. The tradeoff I've hit is that agents running autonomously need it to happen automatically or coherence degrades fast between sessions.

For pruning we landed on a last-touched timestamp + recall frequency counter per memory. Things not accessed in N sessions that were weakly formed to begin with get soft-deleted. Human review before hard delete is probably better UX if your setup allows it.

Curious what "dead ends" look like in yours; conversational chains that didn't resolve, or factual ones?

Re: Agents that run while I sleep

#396

Post by silentsvn »

zhangchen wrote: post #277
silentsvn wrote: post #87

One thing I've been wrestling with building persistent agents is memory quality. Most frameworks treat memory as a vector store — everything goes in, nothing gets resolved. Over time the agent is recalling contradictory facts with equal confidence. The architecture we landed on: ingest goes through a certainty scoring layer before storage. Contradictions get flagged rather than silently stacked. Memories that get rec…

[flagged]

You're right, and it's the part that keeps me up. We handle it with versioned writes — each memory has a createdAt, observedAt, and a validUntil that can be set explicitly or inferred from context. Temporal scope gets embedded as metadata: "as of last session" vs "persistent fact."

Causal ordering is harder. Right now we surface both conflicting versions during retrieval with timestamps and let the agent reason about which is authoritative. It's not a complete solution — the agent can still pick wrong without the right reasoning context.

What you're describing is architecturally the right answer. We haven't built proper write-ordering yet. That's probably where the next cycle goes.

Re: Agents that run while I sleep

#397

Post by humanfromearth9 »

brushfoot wrote: post #342
hi_hi wrote: post #206

This _all_ (waves hands around) sounds like alot of work and expense for something that is meant to make programming easier and cheaper. Writing _all_ (waves hands around various llm wrapper git repos) these frameworks and harnesses, built on top of ever changing models sure doesn't feel sensible. I don't know what the best way of using these things is, but from my personal experience, the defaults get me a looong wa…

> sounds like alot of work and expense for something that is meant to make programming easier and cheaper. It's not more work; it's a convergence of roles. BA/PO/QA/SWE are merging. AI has automated aspects of those roles that have made the traditional separation of concerns less desirable. A new hybrid role is emerging. The person writing these acceptance criteria can be the one guiding the AI to develop them. So no…

Oh a modern comeback of the analyst-programmer?

Re: Agents that run while I sleep

#398

Post by KronisLV »

brobdingnagians wrote: post #300
hi_hi wrote: post #206

This _all_ (waves hands around) sounds like alot of work and expense for something that is meant to make programming easier and cheaper. Writing _all_ (waves hands around various llm wrapper git repos) these frameworks and harnesses, built on top of ever changing models sure doesn't feel sensible. I don't know what the best way of using these things is, but from my personal experience, the defaults get me a looong wa…

I would encourage my competitors to use AI agents on their codebase as much as possible. Make sure every new feature has it, lots of velocity! Run those suckers day and night. Don't review it, just make sure the feature is there! Then when the music stops, the AI companies hit the economic realities, go insolvent, and they are left with no one who understands a sprawling tangled web of code that is 80% AI generated,…

> they are left with no one who understands a sprawling tangled web of code that is 80% [random people that I can't ask because they don't work here anymore and they didn't care to leave docs or comments] generated, then we'll see who laughs last.

Yes, this matches my experience with codebases before AI was a thing.

Re: Agents that run while I sleep

#399

Post by weinzierl »

evrenesat wrote: post #337
brobdingnagians wrote: post #300

Earlier quoted context omitted.

I would encourage my competitors to use AI agents on their codebase as much as possible. Make sure every new feature has it, lots of velocity! Run those suckers day and night. Don't review it, just make sure the feature is there! Then when the music stops, the AI companies hit the economic realities, go insolvent, and they are left with no one who understands a sprawling tangled web of code that is 80% AI generated,…

Qwen3 Coder Next and Qwen3.5-35B-A3B already very good and can be run on today's higher end home computers with good speed. Tomorrow's machines will not be slower but models are keep getting more efficient. A good sw engineer still would be valuable in Tomorrow's world but not as a software assembler.

Not my experience. Current Qwen Coder is noteworthy but still far from good. Can't compare them with current commercial offerings, it is just different leagues.

Re: Agents that run while I sleep

#400

Post by joegaebel »

codethief wrote: post #333
joegaebel wrote: post #149

Earlier quoted context omitted.

I've been able to encode Outside-in Test Driven Development into a repeatable workflow. Claude Code follows it to a T, and I've gotten great results. I've written about it more here, and created a repo people can use out of the box to try it out: https://www.joegaebel.com/articles/principled-agentic-softwa... https://github.com/JoeGaebel/outside-in-tdd-starter

Thanks for sharing! > When asking Claude Code to write tests, I find they are inevitably coupled to implementation details, mockist, brittle, and missing coverage. Interestingly, I haven't noticed any of that so far, using Claude Code on a new-ish project (couple 10k loc). However, I also went out of my way in my CLAUDE.md to instruct it to write functional code, avoid side effects / push side effects to the shell (f…

That's the kicker - you taught it conventions that it follows. Even better (in my view) is to ensure you're getting higher coverage and tests focused on behaviour by getting it to write the tests first.

Even moreso by ensuring it writes "feature complete" tests for each feature first.

Even moreso by running mutation testing to backfill tests for logic it didn't cover.

Post reply on HN