.. HN is actually hilarious We are barely 4 years in since the release of a historically important tech. Of course the next few years are incremental. thats how it always works. Even last year, before opus 4.5,…
any company can roll instagram(just simple image viewer) or whatsapp(just messaging) out though with the same logic. Does not mean you can compete
.. Don't you think it suspicious/sounds too good to be true? A newly created product space with insane margins, and easy to compete in? Easy to compete+huge margins -> lots of competitors who compete on price ->…
Sandboxes look a bit commoditized. You cannot 10x on basically what's just a VM with a few agent-friendly features in 2026. Hence competing on purely price as a new startup is a bad idea imo. As you mentioned…
> This is a classic test request Isn't this basically the model admitting it was trained on this? Otherwise why would it think a pelican svg is a usual request?
No? from a quick skim it doesnt look like it goes into the system prompt everytime, you just use search/grep over it. Pretty much most memory approaches relying on a big set of info where agent chooses what to 'recall'.…
This is very bad logic 1) Humans also are trained on a subset of human knowledge. 2)A lot of papers are just about experimenting something, and then applying simple stats. Eg empirical studies, around 1/3rd of published…
Aware that this is essentially a soon to be deprecated service. As any vendor you need to know the life expectancy of it, plus forecast/predict any pricing changes. You really do not want to become dependent. Even if…
Again, this is HN bubble stuff. The vast majority of people do not mind oauth or account.
> if you hook up to the fediverse No this is the hard problem. HN people live in a bubble. Anything else than signup with oauth and then having access to everyone and its too hard and 99% of people will click away.
Very fascinating, super interesting engineering. Although i do find it very funny how they just bypass a massive vulnerability, basically zero data isolation (even between good actors, let alone bad ones) with 3…
Not all agents have access to a sandbox/cli/code execution environment to run arbitrary api calls etc. MCP helps by essentially having another tool call without needing a sandbox. If you do have a sandbox, then might as…
What is the difference with Livekit Gateway? https://livekit.com/blog/introducing-livekit-inference Or even something more managed like Vapi?
This is terrible. Models have been RLed on looking at the previous tool call chain, and reasoning. No chance this does not reduce performance. The point of compaction is that it also includes useful signal from the tool…
https://github.com/e2b-dev/e2b
> Google DeepMind: We are building strong momentum: Flash is in high demand, our Cyber model is live, and Gemma models have surpassed 900M+ downloads Considering these are the best stats they could find, gemini…
this is /goal in claude code/codex. also basically a slightly improved ralph loop
is this really that surprising? Exploitgym prompts are tuned for a model to do everything it can to achieve a cybersec/exploit task. And we know that models are good at finding vulverabiltiies. Its just random that the…
the OP asked why, you more described the how. What is the benefit of all this?
"Lottery winner says you should not gamble"
Also, the OP just does not understand how the market works anyway. Surely if it was obvious that investing in fresh IPOs is a bad move, all of the big boys (banks, hedge funds etc) would short them to the point of…
.. HN is actually hilarious We are barely 4 years in since the release of a historically important tech. Of course the next few years are incremental. thats how it always works. Even last year, before opus 4.5,…
any company can roll instagram(just simple image viewer) or whatsapp(just messaging) out though with the same logic. Does not mean you can compete
.. Don't you think it suspicious/sounds too good to be true? A newly created product space with insane margins, and easy to compete in? Easy to compete+huge margins -> lots of competitors who compete on price ->…
Sandboxes look a bit commoditized. You cannot 10x on basically what's just a VM with a few agent-friendly features in 2026. Hence competing on purely price as a new startup is a bad idea imo. As you mentioned…
> This is a classic test request Isn't this basically the model admitting it was trained on this? Otherwise why would it think a pelican svg is a usual request?
No? from a quick skim it doesnt look like it goes into the system prompt everytime, you just use search/grep over it. Pretty much most memory approaches relying on a big set of info where agent chooses what to 'recall'.…
This is very bad logic 1) Humans also are trained on a subset of human knowledge. 2)A lot of papers are just about experimenting something, and then applying simple stats. Eg empirical studies, around 1/3rd of published…
Aware that this is essentially a soon to be deprecated service. As any vendor you need to know the life expectancy of it, plus forecast/predict any pricing changes. You really do not want to become dependent. Even if…
Again, this is HN bubble stuff. The vast majority of people do not mind oauth or account.
> if you hook up to the fediverse No this is the hard problem. HN people live in a bubble. Anything else than signup with oauth and then having access to everyone and its too hard and 99% of people will click away.
Very fascinating, super interesting engineering. Although i do find it very funny how they just bypass a massive vulnerability, basically zero data isolation (even between good actors, let alone bad ones) with 3…
Not all agents have access to a sandbox/cli/code execution environment to run arbitrary api calls etc. MCP helps by essentially having another tool call without needing a sandbox. If you do have a sandbox, then might as…
What is the difference with Livekit Gateway? https://livekit.com/blog/introducing-livekit-inference Or even something more managed like Vapi?
This is terrible. Models have been RLed on looking at the previous tool call chain, and reasoning. No chance this does not reduce performance. The point of compaction is that it also includes useful signal from the tool…
https://github.com/e2b-dev/e2b
> Google DeepMind: We are building strong momentum: Flash is in high demand, our Cyber model is live, and Gemma models have surpassed 900M+ downloads Considering these are the best stats they could find, gemini…
this is /goal in claude code/codex. also basically a slightly improved ralph loop
is this really that surprising? Exploitgym prompts are tuned for a model to do everything it can to achieve a cybersec/exploit task. And we know that models are good at finding vulverabiltiies. Its just random that the…
the OP asked why, you more described the how. What is the benefit of all this?
"Lottery winner says you should not gamble"
Also, the OP just does not understand how the market works anyway. Surely if it was obvious that investing in fresh IPOs is a bad move, all of the big boys (banks, hedge funds etc) would short them to the point of…