spion (@spion) profile picture

Still likes programming. ex-Apple. Prefers insightful discussion to debate. LLMs, Rust, TypeScript, Effect, SolidJS, devops, keto, stats, audio/DSP

London, England
Joined February 2008
Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)Photo by spion (@spion)
spion retweeted
Replying to @OpenAI
Ok but you distilled all of humanity
6
3
750
21,375
spion retweeted
So we live in the future and even if YouTube Studio stats are *terrible*, we could create our own, right? Not so easy: today's corporate software is not just bad, is also closed: no API for you.
12
1
1
164
13,180
spion retweeted
this is one of those reasons why I don't think most people will really generate their own software good software is a set of strong opinions and I'd rather have something that's been really thought through by someone else
174
335
106
3,919
205,178
spion retweeted
No one wants to use your agent We want to use your thing with our agent
We messed up. We built an AI PM, but nobody wants another agent. They want to use their own. So we rebuilt the platform. Introducing Modem 2.0: finds problems buried in customer channels, tracks them, and follows up when fixes ship. Works with the agents you use every day.
68
25
20
752
61,789
So far this set of injected instructions (mechanism similar to ponytail) has served me really well github.com/spion/claude-plug… mostly readable code, the units defined are sensible and the unit tests are too, lightweigh process so it doesn't change wait times.
1
3
206
Opus 5.5 is still bad at coming up with property tests based on real business rules, I'm happy enough to correct it when needed but someone who is not interested in property tests might want to leave that part out.
1
59
Would still encourage getting interested in property tests! They are probably the most powerful tool for verification, because they work even when full formal verification is not viable (i.e. most of the time, even with LLMs). They can be better than partial formal verification
2
47
Finally!
Check out Code Mode, a new, experimental way for Claude Code to work with tools. Claude writes scripts that chain your tools together in sophisticated ways, and it can answer you while long commands are still running. Opt in with CLAUDE_CODE_EXPERIMENTAL_CODE_MODE=1 code.claude.com/docs/en/code…
122
MobX no longer requires marking components with @observer, or using generators for async actions! The mobx-react-plugin for Vite / Babel automatically marks components and flows. This also avoids the need to opt-out of React compiler manually. Awesome work by @egorgorv
6
12
2
108
6,974
The number of bad takes on the CloudFlare unwrap() crash confirms my suspicions that almost nobody thinks clear-headedly about programming languages.
1
1
2
152
For servers, the Elixir/Erlang approach is likely one of the best out there, but thinking is still required 😅
1
91
Hah, I got this partly wrong: a crashed process’s mailbox dies with it; So you would only observe the erlang process crashloop problem, not an OOM.
20
I would really like to see a benchmark/test breakdown for LLMs where we actually compare and see different model generations and dig into *why* a newer model does better.
1
62
I suspect we'll largely see that its closely related to ability to do tool calls, understand tool output and whether its wrong/bad and continue more persistently until the issues detected by the tools are resolved
25
This graph gives the art of vagueposting a new, exciting scientific flavor. If the log factor is log2, the increase is 22x. If the log factor is log10, its 30,000x.
This slide from the Anthropic IPO roadshow was a big factor in my decision to leave. It’s an insane plot and I’m surprised they made it public. It shows the compute efficiency of pretraining over time. The y-axis is a **log scale**: they are seeing continued superexponential algorithmic progress. Mythos was not a one-time deviation, but a point on a superexponential. They could already retrain Mythos with a fraction of the compute originally needed. It doesn’t strictly imply a software-only intelligence explosion- they have been spending more on R+D. But algorithmic improvements do not require ridiculous creative genius and are on the verge of being automated. You do the math.
1
99
It could also be a log factor of 1.2 for all we know.
28
Crazy coincidence? 'The agency wrote on Nov. 10 that after the D.C. test, it will “now use SMART in the airspace of all 22 centers across the country to reduce delays, reduce fuel consumption and improve the travel experience for the flying public.” The tech was already being deployed at some airports.' gizmodo.com/the-faa-is-rolli…
3
12
2
31
7,875
A think tank funded by Anthropic, OpenAI and Google is urging the UK government to weaken copyright law to let AI companies train on creatives' work without permission. And it has the gall to say this would "benefit both AI and creators." Shameless.
When Andy Burnham entered Downing Street in July 2026, AI moved to the centre of government. But while the diagnosis is clear, Britain’s delivery is lagging. Our latest briefing explores why – and how government can fix it. Read more smf.co.uk/publications/susta…
13
191
7
596
17,638
surprised that this blew up but also the comments are interesting. lots of chat, monorepos are so easy you just need.. this tool, this esoteric process, this ci magic and all works, and btw I ship faster and obviously more than you some interesting replies from bigger companies broadly agreeing eg. openai rebuilding git, aws doing small repos. most things become distributed as products scale and so I think leaning into that is broadly healthy. whatever way you choose to execute it. a lot of the Artifacts product thinking was following standards and making it simple for agents to work with code at internet scale. Minimal context, minimal tokens, minimal compute. Small repos are recommended!! in our current super secret project we have an Artifacts repo where we deploy staging from. Releases come from our internal source control after a review and merge. This allows everyone’s agent to push straight to main whilst keeping some semblance of control. I do not have any answers. But the dev lifecycle you did last year probs isn’t gonna be how top companies are doing it next year.
hot take: unless you are willing to reimplement git / github (like anthropic), I think monorepos are an antipattern in an age of agents the alternative is to keep things light and make a lovely cli/mcp for agents to do search over your org's code and docs without a checkout
3
2
28
3,659
hot take: unless you are willing to reimplement git / github (like anthropic), I think monorepos are an antipattern in an age of agents the alternative is to keep things light and make a lovely cli/mcp for agents to do search over your org's code and docs without a checkout
139
25
33
819
312,385