dehugger

The ability to understand and maintain inherited projects is more valuable than the ability to create new greenfield projects.

Is Fable 5 just Opus 5 with some additional long-context management modifications for extended self-directed work? Or are they actually truly different models?

Some of us happen to be in positions to make those decisions at our respective companies. What we think does, in fact, matter.

Risk exposure of "internal closed source" vs "open source". No one (external) cares nor can inspect a companies pile of internal utilities and code. As long as the code works than there's no problems.

Everyone and their cat can look at open source projects, which can and will result in being called out publicly. This can also have legal ramifications on the project itself.

I have one of these. Got it a few weeks before the price increases. On the 14" version charging is limited to 96 watts, but the chip can pull north of that with adequate cooling, so the battery will literally drain while plugged in.

It isn't a problem for me, more amusing than anything else (I run in Low Power mode 90% of the time) but worth knowing for anyone thats thinking about pushing the hardware to its limit 24/7.

You are vastly over-estimating the tech power the vast majority of businesses have dedicated to logistics. There's a large number of different systems involved with a enterprise logistics stack. Ecomm store provider, ERPs, middleware, warehouse systems, shipping systems, banking, etc. Which part of the pipeline are you going to hold up while you wait for enough orders to pool to build a meaningful heuristic?

The solution Valve came up with is quite brilliant.

The answer is that once you move past a modest shipping op the people with actual visibility on that would be the warehouse that's fulfilling, also typically people who don't have the power to cancel orders themselves.

Ecomm orders want to drop to the distribution center as soon as possible, which means you can't wait until you have a whole bunch of them just so you can analyze which addresses are on multiple orders. You would either need to 1) detect this in the warehouse systems (I spent my career working on these, so I can say with high certainty that is almost definitely Not going to happen, especially if they go through a 3PL) OR 2) you have to cancel orders after they have already dropped to the warehouse (which means wasted labor in the best-case scenario).

None of that is worth the effort to a company who is fundamentally still getting paid the same for the product regardless of if the purchaser is a scalper or not.

I don't know that I disagree, but this had to be in the works before the IPO right? Acquisitions don't typically materialize in a timeline of <1 week (or perhaps they do when someone walks in and offers 60B...)

I was trying to think about the why with Cursor, and the only thing that makes sense to me is they wanted experts in making harnesses so that they can pivot that expertise towards building harnesses intended for autonomous agents to use instead of humans. There's no world where a 60 billion IDE makes sense.

Not that I've found, and I am up to my fifth row of wood now.

I have completed 4 rows of firewood, onto my 5th! The stacking animation is very satisfying, I am sad I can't actually see the wood stacking anymore (because my wood pile has grown to large). It would be nice if it persisted across refreshes, and maybe provided a counter for how many rounds/cords of would you have split.

Capital, as a whole, barely thinks farther forward than the next fiscal quarter. If you are lucky, the absolute farthest out is end-of-career/lifetime for the current leadership suite. Why would capitalists be the saviors from climate change?

most gen1 apple products are a small retirement investment if you keep it in working condition for long enough

I appreciate everyone's corrections here, my apologies. I clearly misunderstood the situation.

Ah I see, thanks for breaking it down.

Awesome, thats good news. I have a FW Desktop with the 395+ in it and have generally been impressed with it. Hoping that will eventually make its way into these machines.

There is a huge difference between on-die and off-die memory. Where that shared memory is located matters immensely.

Really? Because I did look through the entire spec list they provided and didnt see any non-Intel. Didnt get to the order screen since it was behind a waitlist sign up. I agree, that is better then nothing.

A laptop without a unified memory model is categorically incapable of being the "ultimate developer laptop". Framework already have Strix Halo machines, I don't know why they felt the need to hamstring this thing with Intel.

Late reply, but the answer is: 1) there is a fair amount of behind the scenes work going on that I dont want the agent to have access too or know about. Tools make it very easy to have strong control over what can and cannot be done. File system access is built directly into the tool, which makes it much easier to be confident about what it has access too, since the thing that actually has the permissions is the tools code, not the agent. 2) Portability, I can host it from a single spot and serve it to multiple models on different machines easily, which is very desirable for me. 3) I can update the configuration of the tool independent of a skill.

A skill wouldn't be a bad option though, and I highly recommend creating one yourself! The ability to customize our workflows and tools to a high degree is one of the largest strengths of agentic coding.

I built something similar using an MCP that allows claude to "outsource" development to GLM 4.7 on Cerebras (or a different model, but GLM is what I use). The tool allows Claude to set the system prompt, instructions, specify the output file to write to and crucially allows it to list which additional files (or subsections of files) should be included as context for the prompt.

Ive had great success with it, and it rapidly speeds up development time at fairly minimal cost.

Whats with this assumption that there's no human involvement? I dont just say "hey scan this 2m loc repo and give me some docs'... that would be insane. T

he AI is there to do the easy part; scan a giant spaghetti bowl and label each noodle. The humans job is to attach descriptions to those noodles.

Sometimes I forget that people on this site simply assume the worst in any given situation.

i love the assumption by default that "ai generated" automatically excludes "human verified".

see, i actually read and monitor the outputs. i check them against my own internal knowledge. i trial the results with real trouble shooting and real bug fixes/feature requests.

when its wrong, i fix it. when its right, great we now have documentation where none existed before.

dogfood the documentation and you'll know if its worth using or not.

Yes, correct. Essentially every single industry and tool which rents out capacity of any system or service does this. Your ISP does this. The airline does this. Cruise lines. Cloud computing environments. Restaurants. Rental cars. The list is endless.

surprising considering you just listed two primary use cases (exploring codebases/data models + creating documentation)

I am similarly interested, but mostly because my memory is awful and I'd like to actually remember what people tell me without having to ask repeatedly.

Instructions are more like guidelines than actual rules. LLMs arent deterministic.

If there is an action you don't want them to ever take, dont provide them with the ability to do so.

your github repo was highly entertaining. thanks for make my day a bit brighter:)

What makes you think the dbcredentials or IP are being exposed to Claude? The entire reason I build my own connectors is to avoid having to expose details like that.

What I give Claude is an API key that allows it to talk to the mcp server. Everything else is hidden behind that.

Write your own tools. Dont use something off the shelf. If you want it to read from a database, create a db connector that exposes only the capabilities you want it to have.

This is what I do, and I am 100% confident that Claude cannot drop my database or truncate a table, or read from sensitive tables. I know this because the tool it uses to interface with the database doesn't have those capabilities, thus Claude doesn't have that capability.

It won't save you from Claude maliciously ex-filtrating data it has access to via DNS or some other side channel, but it will protect from worst-case scenarios.