I would be interested to hear your take on Copilot vs Claude. I have used Copilot (trial) in VS Code and I found it to mostly meet my needs. It could generate some plans and code, which I could review on the go. I found this very natural to me as I never felt 'left behind' in whatever code the AI was generating. However, most of the posts I see here are on Claude (I haven't tried it) and very few mentions of Copilot. What is your impression about them and the use cases each is strong in?
(Context: I'm a different person, but have thoughts on this)
I started using Copilot at work because that's what the company policy was. It's a pretty strict environment, but it's perfectly serviceable and gets a lot of fresh, vetted updates. IDE integration with vs code was a huge plus for me.
Claude code is definitely a messier, buggier frontend for the LLM. It's clunkier to navigate and it has much more primitive context management tools. IDE integration is clunky with vs code, too.
However, if you want to take advantage of the Anthropic subscription services, I've found Claude Code is the way to go... Simply because Anthropic works hard to lock you into their ecosystem if you want the sweet discounts. I'm greedy, so I bit the bullet for all of the LLM coding stuff I do in my personal life.
Copilot isn’t really a competing product to Claude - in fact I use Claude through copilot.
I have found in general that for the type of work I do (senior to staff level engineering, 90-10 research to programming) that Claude Opus is the only model really worth my time - but I just really like the Copilot CLI tooling.
I do use LLMs to learn about new subjects but we already only bill 10% for "coding" and that's inflating it to cover other parts.
I can't imagine that slopping it up would be a great decision. Having alien code that no one ever understood between a bug report and a solution. Anthropic isn't going to give us money for our lost contracts, is it?
I would say I'm using it for about half of the "10%" and and a quarter of the "90%".
> I can't imagine that slopping it up would be a great decision. Having alien code that no one ever understood between a bug report and a solution. Anthropic isn't going to give us money for our lost contracts, is it?
Absolutely, that's a real concern. The only time I will let it loose on something is a throwaway project to test something, or a small tool that I know I can write deterministic tests for.
On codebases of any significant size, I'm using it more like a custom domain Stackoverflow search engine.
Fair point on survivorship bias. But, I think SD card being flash memory is technically expected to fail over time, with that failure compounded by the number of write cycles. These cycles are a spec of the SD card. If a section/page of the flash is being overwritten more frequently than the other, then surely it'll fail faster than an SD card whose erase/write cycles are distributed uniformly across all the sections/pages.
This really puts so many modern conflicts into perspective. Everyone sees themselves as victims. Unfortunately, a consensus on who is and isn't a victim will always be highly elusive.
Since January of this year, I have been waiting for a certain MCU (STM32F042K6T6) to be available but still no luck. I get the bigger picture now: there's a shortage at the source. I have to move fast and secure a stock of the rest of the ICs, otherwise this supply-chain issue can be disastrous to small hardware companies.
I'm convinced that, if in-person IEEE meetups were still a thing right now, you could drop a tray of ST Micro chips in the middle of the meeting and watch it devolve into a fistfight in seconds.
+1 for having to be sealed.
We have a handful of companies wanting to sell us needed chips but they are odds and ends, not always packaged. Were always suspect.
This is a (modern, mistaken) conjoining of two similar phrases
- drawing the short stick (where you hold five sticks / matches, in your hand one of which is cut short but no one can tell cos they are held in someone's hand)
- Grabbing the shitty end of the stick. Which seems fairly obvious if a stick was used for any clearing out style work.
(there seems to be no obvious "short end" of a stick)
No. It comes from choosing somebody at random from a whole group. Get thin sticks (branches from any tree), cut them all around 10 cm and one of them cut it shorter (like 5 cm for example). Now hold the entire bunch of sticks in your hand, carefully to have them same height at visible end (hiding in your hand which one is the short one) and let everybody except yourself draw a stick at random. Whoever gets the short one is the one that would do the task at hand. If everybody draws all long sticks you're the one with the short one at the end. Hence the phrasing.
Not as poor countries, but as poorer countries than the ones the parent comment mentioned. The GDP per capita of Saudi Arabia is around $23k - approximately half of that of Sweden, the Netherlands, or the UK.
Qatar is absurdly rich, but the wealth is inequitably distributed (unusually so). Although the GDP per capita is ~60k, the median household income (and the median per-capita income) are considerably lower than the countries the parent comment mentioned.
> The GDP per capita of Saudi Arabia is around $23k - approximately half of that of Sweden
Why are you mentioning nominal GDP, not PPP which is $55 grand according to CIA (which is more than Sweden's and UK's and just a bit less than US's)? If they raise their taxes to the level of Sweden they will have larger nominal GDP although without any increase in the purchasing power.
reply