Hacker News: Incipient

New comment by Incipient in "You only need the frontier model for one single edit"

Incipient — Tue, 21 Jul 2026 09:24:20 +0000

Wait this is new? Large context models figure out the architecture of the request. Miss sized models plan out each requirement, and smaller models implement a tightly detailed task? Isn't this the standard approach?

New comment by Incipient in "Soofi – Sovereign Open Source Foundation Models"

Incipient — Mon, 20 Jul 2026 16:57:20 +0000

But can it, really? It takes a huge amount of time, resources, and knowledge to train a highly capable model. It also takes a huge amount of the same to run them.

Is it ever going to not be centralised?

New comment by Incipient in "Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling"

Incipient — Mon, 20 Jul 2026 16:20:55 +0000

$200/mo for 20x Max is great value - but it's not sustainable and won't last forever. Microsoft gave up. Anthropic will too. I use roughly $10k/mo - at that price it's absolutely not worth it.

I'm genuinely not sure where the balancing point even is.

New comment by Incipient in "Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling"

Incipient — Mon, 20 Jul 2026 16:11:35 +0000

I mean Claude IS replacing people. Even in Australia - Claude + postgres mcp is replacing data/bi people in even small and medium businesses.

New comment by Incipient in "DSLs Enable Reliable Use of LLMs"

Incipient — Wed, 15 Jul 2026 14:04:36 +0000

Blimey there is always a new thing to learn/use/know with AI - keeping up is getting tiring.

New comment by Incipient in "Microsoft deleted my account and OneDrive"

Incipient — Wed, 15 Jul 2026 03:30:32 +0000

Is there a viable alternative to the sync clients - pc/android with cloud/ghost files etc?

New comment by Incipient in "Probably check on your smart appliances"

Incipient — Wed, 15 Jul 2026 03:25:51 +0000

I wish I never thought of it. Just had a recent Samsung TV update, and now it has to sign in EVERY TIME it turns on. I'm considering how to frame it as a warranty job.

New comment by Incipient in "Ask HN: Is anyone experimenting with different ways of using LLMs for coding?"

Incipient — Fri, 03 Jul 2026 07:49:46 +0000

My current approach which I've been testing on two MVPs with what I would call 'moderate success' (but hey, actual success!)

3 tier, philosophy-spec-design. Increasing detail. Design files include db model explanations and pseudocode/function headers - that level of detail.

For each thing I need to change, I have a, prompt ready to go to ask the agent to follow about 5 steps and it outputs a 'reviewfile' with details of what it things about the thing I posited. I review its output. I have another prompt ready to then get an agent to generate a taskfile + update the design documentation. The taskfile explains in great detail what has changed and what needs to be implemented. I review the taskfile and got diffs of the design doc changes. Finally an agent implements the taskfile. I review all changed code and commit.

It gets there, but still definitely misses some stuff. It's very adequate for a MVP I'm finding.

Edit: this seems to only work with Opus. Sonnet can't do it (maybe I'm just lucky and Opus is seriously compensating for an awful approach and I'm just lucky?)

New comment by Incipient in "Kimi K2.7 Code is generally available in GitHub Copilot"

Incipient — Thu, 02 Jul 2026 09:28:39 +0000

I had to do the same. I expect everything will go token pricing, and at that point a LOT of small/mid businesses will drastically change how they use code.

I've swapped to the 20x Claude plan for a month or two to knock out two ideas I need to get it MVP - expecting Claude to go token priced soon.

New comment by Incipient in "Ford AI hiccups push carmaker to rehire ‘gray beard’ inspectors"

Incipient — Sun, 28 Jun 2026 06:08:07 +0000

I have spent a SOLID 3 full days 8h/day (plus long running tasks overnight) thrashing out a random idea for a Web application using purely Opus (mostly Max, sometimes ultracode version). I'm not a project manager, but I genuinely tried a full 3-tier spec out - design->specs->build details.

While it was significantly better than previous attempts, it still misses very basic things - sporadically. Eg. A clear design requirement was essentially adding clients, explained clearly and comprehensively. The ability to add clients was entirely missed in the build and iteration (there were multiple 'please check its all done' separate agent runs/checks).

I can imagine in a fully autonomous deployment, in even moderate complexity, even to this day would still occasionally mess up - badly enough to cause non-trivial business issues.

I haven't managed to really figure out what's the best way, but my latest thinking is really having boil down tasks to almost unit operations "add UI button, wire to Api call. End".

New comment by Incipient in "GLM-5.2 – How to Run Locally"

Incipient — Tue, 23 Jun 2026 16:39:56 +0000

Unless the token estimates I get from using Claude are wayyy out, I burn through 5m+ tokens/day, and I'm not doing a lot of time. 500k tokens in a 24h period for $5k of hardware seems quite poor?

New comment by Incipient in "Databricks Launches LTAP: A Unified OLAP/OLTP Data Architecture"

Incipient — Wed, 17 Jun 2026 00:39:27 +0000

Hey I mean we've been using a fairly basic mssql box for years in a organisation of about 300 and it humms along nicely - granted we have 2 'materialised' aggregate tables/views (done in Python) but the TCO is tiny, and there is very little learning curve.

New comment by Incipient in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

Incipient — Sat, 13 Jun 2026 02:53:48 +0000

Everyone knows a philosophy comes before a spec. Claude has to write your applications philosophy first, then you write your spec. But a philosophy is crap without a values statement, so Claude has to actually write that first.

New comment by Incipient in "Anthropic raises $65B in Series H funding at $965B post-money valuation"

Incipient — Fri, 29 May 2026 03:48:22 +0000

I'm really annoyed at github for only allowing export of a single month of usage.

There were a lot of people (here included) that were absolutely abusing github - getting Opus to generate its own subagents for days on end with a single premium request. If THAT'S $3k/mo, I'm honestly not worried.

I was just asking sonnet, 5.4, opus, in single agent session to fix a problem for 20 minutes...if THAT'S $3k/mo, then AI is truly cooked.

New comment by Incipient in "Memory has grown to nearly two-thirds of AI chip component costs"

Incipient — Mon, 25 May 2026 05:09:46 +0000

I've so far been anti-chinese memory in my recommendations, not because it's Chinese (I don't really trust any big organisation/govt other than the EU?) but because they've been very new, and it's not worth PC stability for saving $50.

However with corsair giving it their blessing, and their technology having matured a bit (a lot?), and more reviews showing good stability (longevity I suppose, is TBD) they're definitely worth recommending these days.

New comment by Incipient in "The seed oil panic is hurting my cardiac patients"

Incipient — Sun, 24 May 2026 15:24:30 +0000

It absolutely is in Australia, and I suspect Europe (from when I went 5 or so years ago). Even mostly possible in Houston when I was there 15 years ago.

The US is even more cooked than I thought if you can get a bunch of fresh veggies from a grocery store.

New comment by Incipient in "'You can hear me now or pay me later' Music exec tells graduates booing AI"

Incipient — Wed, 20 May 2026 10:57:54 +0000

I think art/music is in a weird dichotomy of sorts, for me at least. It's both the most and least impacted by AI. It's trivial to go "hey suno give me music" but I refuse outright to listen to AI music as knowing it's statistical noise (of sorts) I don't really get value/enjoyment out of it.

New comment by Incipient in "Agora-1: The Multi-Agent World Model"

Incipient — Tue, 19 May 2026 04:54:28 +0000

I'm confused how the world itself works - or would work - at scale. Taking that minecraft clip on the link, if I jump down a cave first, and the model decides the cave goes off to the left. A few hours later I come back, and this time the model decides the cave bends to the right?

New comment by Incipient in "SANA-WM, a 2.6B open-source world model for 1-minute 720p video"

Incipient — Sat, 16 May 2026 14:07:35 +0000

Outputting video of that quality/consistency at 1 minute, for a 2.6B model seems insane?

New comment by Incipient in "Vercel’s pricing page"

Incipient — Fri, 01 May 2026 07:27:29 +0000

The only way you can get away with creating an application without touching sql is of you offload the logic to your backend language, and then I don't think you'd be efficient enough to scale.

Also can someone actually understand the logic of joins, indexes, pks, etc enough to create an efficientand scalable db, and not simply have learned sql by proximity?